summaryrefslogtreecommitdiff
path: root/fs/nfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nfs')
-rw-r--r--fs/nfs/callback_proc.c3
-rw-r--r--fs/nfs/callback_xdr.c17
-rw-r--r--fs/nfs/delegation.c9
-rw-r--r--fs/nfs/delegation.h2
-rw-r--r--fs/nfs/dir.c119
-rw-r--r--fs/nfs/direct.c50
-rw-r--r--fs/nfs/file.c2
-rw-r--r--fs/nfs/filelayout/filelayout.c6
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.c200
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayout.h17
-rw-r--r--fs/nfs/flexfilelayout/flexfilelayoutdev.c119
-rw-r--r--fs/nfs/inode.c5
-rw-r--r--fs/nfs/internal.h1
-rw-r--r--fs/nfs/nfs3acl.c43
-rw-r--r--fs/nfs/nfs42.h1
-rw-r--r--fs/nfs/nfs42proc.c107
-rw-r--r--fs/nfs/nfs42xdr.c146
-rw-r--r--fs/nfs/nfs4_fs.h12
-rw-r--r--fs/nfs/nfs4file.c23
-rw-r--r--fs/nfs/nfs4idmap.c2
-rw-r--r--fs/nfs/nfs4proc.c225
-rw-r--r--fs/nfs/nfs4state.c20
-rw-r--r--fs/nfs/nfs4trace.h10
-rw-r--r--fs/nfs/nfs4xdr.c43
-rw-r--r--fs/nfs/nfstrace.h2
-rw-r--r--fs/nfs/pagelist.c6
-rw-r--r--fs/nfs/pnfs.c355
-rw-r--r--fs/nfs/pnfs.h17
-rw-r--r--fs/nfs/pnfs_nfs.c32
-rw-r--r--fs/nfs/super.c9
-rw-r--r--fs/nfs/unlink.c192
-rw-r--r--fs/nfs/write.c60
32 files changed, 1189 insertions, 666 deletions
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 7c9fbf504..aaa2e8d3d 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -217,7 +217,8 @@ static u32 initiate_file_draining(struct nfs_client *clp,
}
if (pnfs_mark_matching_lsegs_return(lo, &free_me_list,
- &args->cbl_range)) {
+ &args->cbl_range,
+ be32_to_cpu(args->cbl_stateid.seqid))) {
rv = NFS4_OK;
goto unlock;
}
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 976c90608..d81f96aac 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -146,10 +146,16 @@ static __be32 decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
p = read_buf(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return htonl(NFS4ERR_RESOURCE);
- memcpy(stateid, p, NFS4_STATEID_SIZE);
+ memcpy(stateid->data, p, NFS4_STATEID_SIZE);
return 0;
}
+static __be32 decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound_hdr_arg *hdr)
{
__be32 *p;
@@ -211,7 +217,7 @@ static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr,
__be32 *p;
__be32 status;
- status = decode_stateid(xdr, &args->stateid);
+ status = decode_delegation_stateid(xdr, &args->stateid);
if (unlikely(status != 0))
goto out;
p = read_buf(xdr, 4);
@@ -227,6 +233,11 @@ out:
}
#if defined(CONFIG_NFS_V4_1)
+static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
struct xdr_stream *xdr,
@@ -263,7 +274,7 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
}
p = xdr_decode_hyper(p, &args->cbl_range.offset);
p = xdr_decode_hyper(p, &args->cbl_range.length);
- status = decode_stateid(xdr, &args->cbl_stateid);
+ status = decode_layout_stateid(xdr, &args->cbl_stateid);
if (unlikely(status != 0))
goto out;
} else if (args->cbl_recall_type == RETURN_FSID) {
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5166adcfc..322c2585b 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -875,15 +875,16 @@ int nfs_delegations_present(struct nfs_client *clp)
/**
* nfs4_copy_delegation_stateid - Copy inode's state ID information
- * @dst: stateid data structure to fill in
* @inode: inode to check
* @flags: delegation type requirement
+ * @dst: stateid data structure to fill in
+ * @cred: optional argument to retrieve credential
*
* Returns "true" and fills in "dst->data" * if inode had a delegation,
* otherwise "false" is returned.
*/
-bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
- fmode_t flags)
+bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags,
+ nfs4_stateid *dst, struct rpc_cred **cred)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_delegation *delegation;
@@ -896,6 +897,8 @@ bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode,
if (ret) {
nfs4_stateid_copy(dst, &delegation->stateid);
nfs_mark_delegation_referenced(delegation);
+ if (cred)
+ *cred = get_rpccred(delegation->cred);
}
rcu_read_unlock();
return ret;
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 333063e03..64724d252 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -56,7 +56,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
-bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
+bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, struct rpc_cred **cred);
void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
int nfs4_have_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index a7dd1fee8..19d93d0cd 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -57,7 +57,7 @@ static void nfs_readdir_clear_array(struct page*);
const struct file_operations nfs_dir_operations = {
.llseek = nfs_llseek_dir,
.read = generic_read_dir,
- .iterate = nfs_readdir,
+ .iterate_shared = nfs_readdir,
.open = nfs_opendir,
.release = nfs_closedir,
.fsync = nfs_fsync_dir,
@@ -145,6 +145,7 @@ struct nfs_cache_array_entry {
};
struct nfs_cache_array {
+ atomic_t refcount;
int size;
int eof_index;
u64 last_cookie;
@@ -200,11 +201,20 @@ void nfs_readdir_clear_array(struct page *page)
int i;
array = kmap_atomic(page);
- for (i = 0; i < array->size; i++)
- kfree(array->array[i].string.name);
+ if (atomic_dec_and_test(&array->refcount))
+ for (i = 0; i < array->size; i++)
+ kfree(array->array[i].string.name);
kunmap_atomic(array);
}
+static bool grab_page(struct page *page)
+{
+ struct nfs_cache_array *array = kmap_atomic(page);
+ bool res = atomic_inc_not_zero(&array->refcount);
+ kunmap_atomic(array);
+ return res;
+}
+
/*
* the caller is responsible for freeing qstr.name
* when called by nfs_readdir_add_to_array, the strings will be freed in
@@ -414,12 +424,17 @@ static int xdr_decode(nfs_readdir_descriptor_t *desc,
static
int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
{
+ struct inode *inode;
struct nfs_inode *nfsi;
if (d_really_is_negative(dentry))
return 0;
- nfsi = NFS_I(d_inode(dentry));
+ inode = d_inode(dentry);
+ if (is_bad_inode(inode) || NFS_STALE(inode))
+ return 0;
+
+ nfsi = NFS_I(inode);
if (entry->fattr->fileid == nfsi->fileid)
return 1;
if (nfs_compare_fh(entry->fh, &nfsi->fh) == 0)
@@ -470,6 +485,7 @@ static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
{
struct qstr filename = QSTR_INIT(entry->name, entry->len);
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
struct dentry *dentry;
struct dentry *alias;
struct inode *dir = d_inode(parent);
@@ -489,7 +505,13 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
filename.hash = full_name_hash(filename.name, filename.len);
dentry = d_lookup(parent, &filename);
- if (dentry != NULL) {
+again:
+ if (!dentry) {
+ dentry = d_alloc_parallel(parent, &filename, &wq);
+ if (IS_ERR(dentry))
+ return;
+ }
+ if (!d_in_lookup(dentry)) {
/* Is there a mountpoint here? If so, just exit */
if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
&entry->fattr->fsid))
@@ -503,26 +525,21 @@ void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
} else {
d_invalidate(dentry);
dput(dentry);
+ dentry = NULL;
+ goto again;
}
}
- dentry = d_alloc(parent, &filename);
- if (dentry == NULL)
- return;
-
inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr, entry->label);
- if (IS_ERR(inode))
- goto out;
-
alias = d_splice_alias(inode, dentry);
- if (IS_ERR(alias))
- goto out;
- else if (alias) {
- nfs_set_verifier(alias, nfs_save_change_attribute(dir));
- dput(alias);
- } else
- nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
-
+ d_lookup_done(dentry);
+ if (alias) {
+ if (IS_ERR(alias))
+ goto out;
+ dput(dentry);
+ dentry = alias;
+ }
+ nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out:
dput(dentry);
}
@@ -643,6 +660,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
goto out_label_free;
}
memset(array, 0, sizeof(struct nfs_cache_array));
+ atomic_set(&array->refcount, 1);
array->eof_index = -1;
status = nfs_readdir_alloc_pages(pages, array_size);
@@ -705,8 +723,7 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
static
void cache_page_release(nfs_readdir_descriptor_t *desc)
{
- if (!desc->page->mapping)
- nfs_readdir_clear_array(desc->page);
+ nfs_readdir_clear_array(desc->page);
put_page(desc->page);
desc->page = NULL;
}
@@ -714,8 +731,16 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
static
struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
{
- return read_cache_page(file_inode(desc->file)->i_mapping,
+ struct page *page;
+
+ for (;;) {
+ page = read_cache_page(file_inode(desc->file)->i_mapping,
desc->page_index, (filler_t *)nfs_readdir_filler, desc);
+ if (IS_ERR(page) || grab_page(page))
+ break;
+ put_page(page);
+ }
+ return page;
}
/*
@@ -889,7 +914,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->decode = NFS_PROTO(inode)->decode_dirent;
desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
- nfs_block_sillyrename(dentry);
if (ctx->pos == 0 || nfs_dir_mapping_need_revalidate(inode))
res = nfs_revalidate_mapping(inode, file->f_mapping);
if (res < 0)
@@ -925,7 +949,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
break;
} while (!desc->eof);
out:
- nfs_unblock_sillyrename(dentry);
if (res > 0)
res = 0;
dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
@@ -934,13 +957,11 @@ out:
static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
- struct inode *inode = file_inode(filp);
struct nfs_open_dir_context *dir_ctx = filp->private_data;
dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
filp, offset, whence);
- inode_lock(inode);
switch (whence) {
case 1:
offset += filp->f_pos;
@@ -948,16 +969,13 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
if (offset >= 0)
break;
default:
- offset = -EINVAL;
- goto out;
+ return -EINVAL;
}
if (offset != filp->f_pos) {
filp->f_pos = offset;
dir_ctx->dir_cookie = 0;
dir_ctx->duped = 0;
}
-out:
- inode_unlock(inode);
return offset;
}
@@ -1350,7 +1368,6 @@ EXPORT_SYMBOL_GPL(nfs_dentry_operations);
struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
struct dentry *res;
- struct dentry *parent;
struct inode *inode = NULL;
struct nfs_fh *fhandle = NULL;
struct nfs_fattr *fattr = NULL;
@@ -1380,10 +1397,8 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
if (IS_ERR(label))
goto out;
- parent = dentry->d_parent;
/* Protect against concurrent sillydeletes */
trace_nfs_lookup_enter(dir, dentry, flags);
- nfs_block_sillyrename(parent);
error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
if (error == -ENOENT)
goto no_entry;
@@ -1408,7 +1423,6 @@ no_entry:
}
nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
out_unblock_sillyrename:
- nfs_unblock_sillyrename(parent);
trace_nfs_lookup_exit(dir, dentry, flags, error);
nfs4_label_free(label);
out:
@@ -1471,11 +1485,13 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
struct file *file, unsigned open_flags,
umode_t mode, int *opened)
{
+ DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
struct nfs_open_context *ctx;
struct dentry *res;
struct iattr attr = { .ia_valid = ATTR_OPEN };
struct inode *inode;
unsigned int lookup_flags = 0;
+ bool switched = false;
int err;
/* Expect a negative dentry */
@@ -1490,7 +1506,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
/* NFS only supports OPEN on regular files */
if ((open_flags & O_DIRECTORY)) {
- if (!d_unhashed(dentry)) {
+ if (!d_in_lookup(dentry)) {
/*
* Hashed negative dentry with O_DIRECTORY: dentry was
* revalidated and is fine, no need to perform lookup
@@ -1514,15 +1530,24 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
attr.ia_size = 0;
}
+ if (!(open_flags & O_CREAT) && !d_in_lookup(dentry)) {
+ d_drop(dentry);
+ switched = true;
+ dentry = d_alloc_parallel(dentry->d_parent,
+ &dentry->d_name, &wq);
+ if (IS_ERR(dentry))
+ return PTR_ERR(dentry);
+ if (unlikely(!d_in_lookup(dentry)))
+ return finish_no_open(file, dentry);
+ }
+
ctx = create_nfs_open_context(dentry, open_flags);
err = PTR_ERR(ctx);
if (IS_ERR(ctx))
goto out;
trace_nfs_atomic_open_enter(dir, ctx, open_flags);
- nfs_block_sillyrename(dentry->d_parent);
inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
- nfs_unblock_sillyrename(dentry->d_parent);
if (IS_ERR(inode)) {
err = PTR_ERR(inode);
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
@@ -1551,14 +1576,23 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
put_nfs_open_context(ctx);
out:
+ if (unlikely(switched)) {
+ d_lookup_done(dentry);
+ dput(dentry);
+ }
return err;
no_open:
res = nfs_lookup(dir, dentry, lookup_flags);
- err = PTR_ERR(res);
+ if (switched) {
+ d_lookup_done(dentry);
+ if (!res)
+ res = dentry;
+ else
+ dput(dentry);
+ }
if (IS_ERR(res))
- goto out;
-
+ return PTR_ERR(res);
return finish_no_open(file, res);
}
EXPORT_SYMBOL_GPL(nfs_atomic_open);
@@ -1766,7 +1800,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
trace_nfs_rmdir_enter(dir, dentry);
if (d_really_is_positive(dentry)) {
- nfs_wait_on_sillyrename(dentry);
+ down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
/* Ensure the VFS deletes this inode */
switch (error) {
@@ -1776,6 +1810,7 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
case -ENOENT:
nfs_dentry_handle_enoent(dentry);
}
+ up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
} else
error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
trace_nfs_rmdir_exit(dir, dentry, error);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index c93826e4a..c7326c2af 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -87,6 +87,7 @@ struct nfs_direct_req {
int mirror_count;
ssize_t count, /* bytes actually processed */
+ max_count, /* max expected count */
bytes_left, /* bytes left to be sent */
io_start, /* start of IO */
error; /* any reported error */
@@ -123,6 +124,8 @@ nfs_direct_good_bytes(struct nfs_direct_req *dreq, struct nfs_pgio_header *hdr)
int i;
ssize_t count;
+ WARN_ON_ONCE(dreq->count >= dreq->max_count);
+
if (dreq->mirror_count == 1) {
dreq->mirrors[hdr->pgio_mirror_idx].count += hdr->good_bytes;
dreq->count += hdr->good_bytes;
@@ -250,7 +253,7 @@ static int nfs_direct_cmp_commit_data_verf(struct nfs_direct_req *dreq,
* shunt off direct read and write requests before the VFS gets them,
* so this method is only ever called for swap.
*/
-ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
+ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
struct inode *inode = iocb->ki_filp->f_mapping->host;
@@ -261,7 +264,7 @@ ssize_t nfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t pos)
VM_BUG_ON(iov_iter_count(iter) != PAGE_SIZE);
if (iov_iter_rw(iter) == READ)
- return nfs_file_direct_read(iocb, iter, pos);
+ return nfs_file_direct_read(iocb, iter);
return nfs_file_direct_write(iocb, iter);
}
@@ -275,7 +278,7 @@ static void nfs_direct_release_pages(struct page **pages, unsigned int npages)
void nfs_init_cinfo_from_dreq(struct nfs_commit_info *cinfo,
struct nfs_direct_req *dreq)
{
- cinfo->lock = &dreq->inode->i_lock;
+ cinfo->inode = dreq->inode;
cinfo->mds = &dreq->mds_cinfo;
cinfo->ds = &dreq->ds_cinfo;
cinfo->dreq = dreq;
@@ -350,10 +353,12 @@ static ssize_t nfs_direct_wait(struct nfs_direct_req *dreq)
result = wait_for_completion_killable(&dreq->completion);
+ if (!result) {
+ result = dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
if (!result)
result = dreq->error;
- if (!result)
- result = dreq->count;
out:
return (ssize_t) result;
@@ -383,8 +388,10 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
if (dreq->iocb) {
long res = (long) dreq->error;
- if (!res)
+ if (dreq->count != 0) {
res = (long) dreq->count;
+ WARN_ON_ONCE(dreq->count < 0);
+ }
dreq->iocb->ki_complete(dreq->iocb, res, 0);
}
@@ -396,7 +403,7 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq, bool write)
static void nfs_direct_readpage_release(struct nfs_page *req)
{
dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
- d_inode(req->wb_context->dentry)->i_sb->s_id,
+ req->wb_context->dentry->d_sb->s_id,
(unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
req->wb_bytes,
(long long)req_offset(req));
@@ -545,7 +552,6 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_read - file direct read operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers into which to read data
- * @pos: byte offset in file where reading starts
*
* We use this function for direct reads instead of calling
* generic_file_aio_read() in order to avoid gfar's check to see if
@@ -561,8 +567,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
* client must read the updated atime from the server back into its
* cache.
*/
-ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
- loff_t pos)
+ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
@@ -574,7 +579,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
dfprintk(FILE, "NFS: direct read(%pD2, %zd@%Ld)\n",
- file, count, (long long) pos);
+ file, count, (long long) iocb->ki_pos);
result = 0;
if (!count)
@@ -593,8 +598,8 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
goto out_unlock;
dreq->inode = inode;
- dreq->bytes_left = count;
- dreq->io_start = pos;
+ dreq->bytes_left = dreq->max_count = count;
+ dreq->io_start = iocb->ki_pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
if (IS_ERR(l_ctx)) {
@@ -606,14 +611,14 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter,
dreq->iocb = iocb;
NFS_I(inode)->read_io += count;
- result = nfs_direct_read_schedule_iovec(dreq, iter, pos);
+ result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
inode_unlock(inode);
if (!result) {
result = nfs_direct_wait(dreq);
if (result > 0)
- iocb->ki_pos = pos + result;
+ iocb->ki_pos += result;
}
nfs_direct_req_release(dreq);
@@ -632,13 +637,13 @@ nfs_direct_write_scan_commit_list(struct inode *inode,
struct list_head *list,
struct nfs_commit_info *cinfo)
{
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
#ifdef CONFIG_NFS_V4_1
if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
#endif
nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
@@ -673,13 +678,13 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
if (!nfs_pageio_add_request(&desc, req)) {
nfs_list_remove_request(req);
nfs_list_add_request(req, &failed);
- spin_lock(cinfo.lock);
+ spin_lock(&cinfo.inode->i_lock);
dreq->flags = 0;
if (desc.pg_error < 0)
dreq->error = desc.pg_error;
else
dreq->error = -EIO;
- spin_unlock(cinfo.lock);
+ spin_unlock(&cinfo.inode->i_lock);
}
nfs_release_request(req);
}
@@ -969,7 +974,6 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
* nfs_file_direct_write - file direct write operation for NFS files
* @iocb: target I/O control block
* @iter: vector of user buffers from which to write data
- * @pos: byte offset in file where writing starts
*
* We use this function for direct writes instead of calling
* generic_file_aio_write() in order to avoid taking the inode
@@ -1026,7 +1030,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
goto out_unlock;
dreq->inode = inode;
- dreq->bytes_left = iov_iter_count(iter);
+ dreq->bytes_left = dreq->max_count = iov_iter_count(iter);
dreq->io_start = pos;
dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
l_ctx = nfs_get_lock_context(dreq->ctx);
@@ -1057,7 +1061,9 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
if (i_size_read(inode) < iocb->ki_pos)
i_size_write(inode, iocb->ki_pos);
spin_unlock(&inode->i_lock);
- generic_write_sync(file, pos, result);
+
+ /* XXX: should check the generic_write_sync retval */
+ generic_write_sync(iocb, result);
}
}
nfs_direct_req_release(dreq);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index be01095b9..717a8d6af 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -164,7 +164,7 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to)
ssize_t result;
if (iocb->ki_flags & IOCB_DIRECT)
- return nfs_file_direct_read(iocb, to, iocb->ki_pos);
+ return nfs_file_direct_read(iocb, to);
dprintk("NFS: read(%pD2, %zu@%lu)\n",
iocb->ki_filp,
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 3384dc8e6..aa5975738 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -795,7 +795,7 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
buckets[i].direct_verf.committed = NFS_INVALID_STABLE_HOW;
}
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->ds->nbuckets >= size)
goto out;
for (i = 0; i < cinfo->ds->nbuckets; i++) {
@@ -811,7 +811,7 @@ filelayout_alloc_commit_info(struct pnfs_layout_segment *lseg,
swap(cinfo->ds->buckets, buckets);
cinfo->ds->nbuckets = size;
out:
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
kfree(buckets);
return 0;
}
@@ -890,6 +890,7 @@ filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_READ,
+ false,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -915,6 +916,7 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 0cb1abd53..0e8018bc9 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -26,6 +26,8 @@
#define FF_LAYOUT_POLL_RETRY_MAX (15*HZ)
+static struct group_info *ff_zero_group;
+
static struct pnfs_layout_hdr *
ff_layout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
{
@@ -53,14 +55,15 @@ ff_layout_free_layout_hdr(struct pnfs_layout_hdr *lo)
kfree(FF_LAYOUT_FROM_HDR(lo));
}
-static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+static int decode_pnfs_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
{
__be32 *p;
p = xdr_inline_decode(xdr, NFS4_STATEID_SIZE);
if (unlikely(p == NULL))
return -ENOBUFS;
- memcpy(stateid, p, NFS4_STATEID_SIZE);
+ stateid->type = NFS4_PNFS_DS_STATEID_TYPE;
+ memcpy(stateid->data, p, NFS4_STATEID_SIZE);
dprintk("%s: stateid id= [%x%x%x%x]\n", __func__,
p[0], p[1], p[2], p[3]);
return 0;
@@ -211,10 +214,16 @@ static struct nfs4_ff_layout_mirror *ff_layout_alloc_mirror(gfp_t gfp_flags)
static void ff_layout_free_mirror(struct nfs4_ff_layout_mirror *mirror)
{
+ struct rpc_cred *cred;
+
ff_layout_remove_mirror(mirror);
kfree(mirror->fh_versions);
- if (mirror->cred)
- put_rpccred(mirror->cred);
+ cred = rcu_access_pointer(mirror->ro_cred);
+ if (cred)
+ put_rpccred(cred);
+ cred = rcu_access_pointer(mirror->rw_cred);
+ if (cred)
+ put_rpccred(cred);
nfs4_ff_layout_put_deviceid(mirror->mirror_ds);
kfree(mirror);
}
@@ -290,6 +299,8 @@ ff_lseg_merge(struct pnfs_layout_segment *new,
{
u64 new_end, old_end;
+ if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
+ return false;
if (new->pls_range.iomode != old->pls_range.iomode)
return false;
old_end = pnfs_calc_offset_end(old->pls_range.offset,
@@ -310,8 +321,6 @@ ff_lseg_merge(struct pnfs_layout_segment *new,
new_end);
if (test_bit(NFS_LSEG_ROC, &old->pls_flags))
set_bit(NFS_LSEG_ROC, &new->pls_flags);
- if (test_bit(NFS_LSEG_LAYOUTRETURN, &old->pls_flags))
- set_bit(NFS_LSEG_LAYOUTRETURN, &new->pls_flags);
return true;
}
@@ -407,8 +416,9 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
struct nfs4_ff_layout_mirror *mirror;
struct nfs4_deviceid devid;
struct nfs4_deviceid_node *idnode;
- u32 ds_count;
- u32 fh_count;
+ struct auth_cred acred = { .group_info = ff_zero_group };
+ struct rpc_cred __rcu *cred;
+ u32 ds_count, fh_count, id;
int j;
rc = -EIO;
@@ -456,7 +466,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
fls->mirror_array[i]->efficiency = be32_to_cpup(p);
/* stateid */
- rc = decode_stateid(&stream, &fls->mirror_array[i]->stateid);
+ rc = decode_pnfs_stateid(&stream, &fls->mirror_array[i]->stateid);
if (rc)
goto out_err_free;
@@ -484,24 +494,49 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
fls->mirror_array[i]->fh_versions_cnt = fh_count;
/* user */
- rc = decode_name(&stream, &fls->mirror_array[i]->uid);
+ rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
+ acred.uid = make_kuid(&init_user_ns, id);
+
/* group */
- rc = decode_name(&stream, &fls->mirror_array[i]->gid);
+ rc = decode_name(&stream, &id);
if (rc)
goto out_err_free;
+ acred.gid = make_kgid(&init_user_ns, id);
+
+ /* find the cred for it */
+ rcu_assign_pointer(cred, rpc_lookup_generic_cred(&acred, 0, gfp_flags));
+ if (IS_ERR(cred)) {
+ rc = PTR_ERR(cred);
+ goto out_err_free;
+ }
+
+ if (lgr->range.iomode == IOMODE_READ)
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ else
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+
mirror = ff_layout_add_mirror(lh, fls->mirror_array[i]);
if (mirror != fls->mirror_array[i]) {
+ /* swap cred ptrs so free_mirror will clean up old */
+ if (lgr->range.iomode == IOMODE_READ) {
+ cred = xchg(&mirror->ro_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->ro_cred, cred);
+ } else {
+ cred = xchg(&mirror->rw_cred, cred);
+ rcu_assign_pointer(fls->mirror_array[i]->rw_cred, cred);
+ }
ff_layout_free_mirror(fls->mirror_array[i]);
fls->mirror_array[i] = mirror;
}
- dprintk("%s: uid %d gid %d\n", __func__,
- fls->mirror_array[i]->uid,
- fls->mirror_array[i]->gid);
+ dprintk("%s: iomode %s uid %u gid %u\n", __func__,
+ lgr->range.iomode == IOMODE_READ ? "READ" : "RW",
+ from_kuid(&init_user_ns, acred.uid),
+ from_kgid(&init_user_ns, acred.gid));
}
p = xdr_inline_decode(&stream, 4);
@@ -745,7 +780,7 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
else {
int i;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->ds->nbuckets != 0)
kfree(buckets);
else {
@@ -759,7 +794,7 @@ ff_layout_alloc_commit_info(struct pnfs_layout_segment *lseg,
NFS_INVALID_STABLE_HOW;
}
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
return 0;
}
}
@@ -786,6 +821,36 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg,
}
static void
+ff_layout_pg_get_read(struct nfs_pageio_descriptor *pgio,
+ struct nfs_page *req,
+ bool strict_iomode)
+{
+retry_strict:
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
+ req->wb_context,
+ 0,
+ NFS4_MAX_UINT64,
+ IOMODE_READ,
+ strict_iomode,
+ GFP_KERNEL);
+ if (IS_ERR(pgio->pg_lseg)) {
+ pgio->pg_error = PTR_ERR(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
+ }
+
+ /* If we don't have checking, do get a IOMODE_RW
+ * segment, and the server wants to avoid READs
+ * there, then retry!
+ */
+ if (pgio->pg_lseg && !strict_iomode &&
+ ff_layout_avoid_read_on_rw(pgio->pg_lseg)) {
+ strict_iomode = true;
+ goto retry_strict;
+ }
+}
+
+static void
ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req)
{
@@ -795,26 +860,23 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
int ds_idx;
/* Use full layout for now */
- if (!pgio->pg_lseg) {
- pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
- req->wb_context,
- 0,
- NFS4_MAX_UINT64,
- IOMODE_READ,
- GFP_KERNEL);
- if (IS_ERR(pgio->pg_lseg)) {
- pgio->pg_error = PTR_ERR(pgio->pg_lseg);
- pgio->pg_lseg = NULL;
- return;
- }
- }
+ if (!pgio->pg_lseg)
+ ff_layout_pg_get_read(pgio, req, false);
+ else if (ff_layout_avoid_read_on_rw(pgio->pg_lseg))
+ ff_layout_pg_get_read(pgio, req, true);
+
/* If no lseg, fall back to read through mds */
if (pgio->pg_lseg == NULL)
goto out_mds;
ds = ff_layout_choose_best_ds_for_read(pgio->pg_lseg, 0, &ds_idx);
- if (!ds)
- goto out_mds;
+ if (!ds) {
+ if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
+ goto out_pnfs;
+ else
+ goto out_mds;
+ }
+
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
pgio->pg_mirror_idx = ds_idx;
@@ -828,6 +890,12 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_read_mds(pgio);
+ return;
+
+out_pnfs:
+ pnfs_set_lo_fail(pgio->pg_lseg);
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
}
static void
@@ -847,6 +915,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -870,8 +939,12 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
for (i = 0; i < pgio->pg_mirror_count; i++) {
ds = nfs4_ff_layout_prepare_ds(pgio->pg_lseg, i, true);
- if (!ds)
- goto out_mds;
+ if (!ds) {
+ if (ff_layout_no_fallback_to_mds(pgio->pg_lseg))
+ goto out_pnfs;
+ else
+ goto out_mds;
+ }
pgm = &pgio->pg_mirrors[i];
mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].wsize;
@@ -883,6 +956,12 @@ out_mds:
pnfs_put_lseg(pgio->pg_lseg);
pgio->pg_lseg = NULL;
nfs_pageio_reset_write_mds(pgio);
+ return;
+
+out_pnfs:
+ pnfs_set_lo_fail(pgio->pg_lseg);
+ pnfs_put_lseg(pgio->pg_lseg);
+ pgio->pg_lseg = NULL;
}
static unsigned int
@@ -895,6 +974,7 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio,
0,
NFS4_MAX_UINT64,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -1067,8 +1147,7 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
rpc_wake_up(&tbl->slot_tbl_waitq);
/* fall through */
default:
- if (ff_layout_no_fallback_to_mds(lseg) ||
- ff_layout_has_available_ds(lseg))
+ if (ff_layout_avoid_mds_available_ds(lseg))
return -NFS4ERR_RESET_TO_PNFS;
reset:
dprintk("%s Retry through MDS. Error %d\n", __func__,
@@ -1215,8 +1294,6 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
hdr->pgio_mirror_idx + 1,
&hdr->pgio_mirror_idx))
goto out_eagain;
- set_bit(NFS_LAYOUT_RETURN_REQUESTED,
- &hdr->lseg->pls_layout->plh_flags);
pnfs_read_resend_pnfs(hdr);
return task->tk_status;
case -NFS4ERR_RESET_TO_MDS:
@@ -1260,7 +1337,7 @@ ff_layout_set_layoutcommit(struct nfs_pgio_header *hdr)
}
static bool
-ff_layout_reset_to_mds(struct pnfs_layout_segment *lseg, int idx)
+ff_layout_device_unavailable(struct pnfs_layout_segment *lseg, int idx)
{
/* No mirroring for now */
struct nfs4_deviceid_node *node = FF_LAYOUT_DEVID_NODE(lseg, idx);
@@ -1297,16 +1374,10 @@ static int ff_layout_read_prepare_common(struct rpc_task *task,
rpc_exit(task, -EIO);
return -EIO;
}
- if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
- dprintk("%s task %u reset io to MDS\n", __func__, task->tk_pid);
- if (ff_layout_has_available_ds(hdr->lseg))
- pnfs_read_resend_pnfs(hdr);
- else
- ff_layout_reset_read(hdr);
- rpc_exit(task, 0);
+ if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
+ rpc_exit(task, -EHOSTDOWN);
return -EAGAIN;
}
- hdr->pgio_done_cb = ff_layout_read_done_cb;
ff_layout_read_record_layoutstats_start(task, hdr);
return 0;
@@ -1496,14 +1567,8 @@ static int ff_layout_write_prepare_common(struct rpc_task *task,
return -EIO;
}
- if (ff_layout_reset_to_mds(hdr->lseg, hdr->pgio_mirror_idx)) {
- bool retry_pnfs;
-
- retry_pnfs = ff_layout_has_available_ds(hdr->lseg);
- dprintk("%s task %u reset io to %s\n", __func__,
- task->tk_pid, retry_pnfs ? "pNFS" : "MDS");
- ff_layout_reset_write(hdr, retry_pnfs);
- rpc_exit(task, 0);
+ if (ff_layout_device_unavailable(hdr->lseg, hdr->pgio_mirror_idx)) {
+ rpc_exit(task, -EHOSTDOWN);
return -EAGAIN;
}
@@ -1712,7 +1777,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
goto out_failed;
ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
goto out_failed;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1720,6 +1785,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
dprintk("%s USE DS: %s cl_count %d vers %d\n", __func__,
ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count), vers);
+ hdr->pgio_done_cb = ff_layout_read_done_cb;
atomic_inc(&ds->ds_clp->cl_count);
hdr->ds_clp = ds->ds_clp;
fh = nfs4_ff_layout_select_ds_fh(lseg, idx);
@@ -1737,11 +1803,11 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
vers == 3 ? &ff_layout_read_call_ops_v3 :
&ff_layout_read_call_ops_v4,
0, RPC_TASK_SOFTCONN);
-
+ put_rpccred(ds_cred);
return PNFS_ATTEMPTED;
out_failed:
- if (ff_layout_has_available_ds(lseg))
+ if (ff_layout_avoid_mds_available_ds(lseg))
return PNFS_TRY_AGAIN;
return PNFS_NOT_ATTEMPTED;
}
@@ -1769,7 +1835,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
return PNFS_NOT_ATTEMPTED;
ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
return PNFS_NOT_ATTEMPTED;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1798,6 +1864,7 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
vers == 3 ? &ff_layout_write_call_ops_v3 :
&ff_layout_write_call_ops_v4,
sync, RPC_TASK_SOFTCONN);
+ put_rpccred(ds_cred);
return PNFS_ATTEMPTED;
}
@@ -1824,7 +1891,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
struct rpc_clnt *ds_clnt;
struct rpc_cred *ds_cred;
u32 idx;
- int vers;
+ int vers, ret;
struct nfs_fh *fh;
idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
@@ -1838,7 +1905,7 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
goto out_err;
ds_cred = ff_layout_get_ds_cred(lseg, idx, data->cred);
- if (IS_ERR(ds_cred))
+ if (!ds_cred)
goto out_err;
vers = nfs4_ff_layout_ds_version(lseg, idx);
@@ -1854,10 +1921,12 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
if (fh)
data->args.fh = fh;
- return nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
+ ret = nfs_initiate_commit(ds_clnt, data, ds->ds_clp->rpc_ops,
vers == 3 ? &ff_layout_commit_call_ops_v3 :
&ff_layout_commit_call_ops_v4,
how, RPC_TASK_SOFTCONN);
+ put_rpccred(ds_cred);
+ return ret;
out_err:
pnfs_generic_prepare_to_resend_writes(data);
pnfs_generic_commit_release(data);
@@ -2223,6 +2292,11 @@ static int __init nfs4flexfilelayout_init(void)
{
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Registering...\n",
__func__);
+ if (!ff_zero_group) {
+ ff_zero_group = groups_alloc(0);
+ if (!ff_zero_group)
+ return -ENOMEM;
+ }
return pnfs_register_layoutdriver(&flexfilelayout_type);
}
@@ -2231,6 +2305,10 @@ static void __exit nfs4flexfilelayout_exit(void)
printk(KERN_INFO "%s: NFSv4 Flexfile Layout Driver Unregistering...\n",
__func__);
pnfs_unregister_layoutdriver(&flexfilelayout_type);
+ if (ff_zero_group) {
+ put_group_info(ff_zero_group);
+ ff_zero_group = NULL;
+ }
}
MODULE_ALIAS("nfs-layouttype4-4");
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index dd353bb7d..1bcdb15d0 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -10,7 +10,8 @@
#define FS_NFS_NFS4FLEXFILELAYOUT_H
#define FF_FLAGS_NO_LAYOUTCOMMIT 1
-#define FF_FLAGS_NO_IO_THRU_MDS 2
+#define FF_FLAGS_NO_IO_THRU_MDS 2
+#define FF_FLAGS_NO_READ_IO 4
#include "../pnfs.h"
@@ -76,9 +77,8 @@ struct nfs4_ff_layout_mirror {
u32 fh_versions_cnt;
struct nfs_fh *fh_versions;
nfs4_stateid stateid;
- u32 uid;
- u32 gid;
- struct rpc_cred *cred;
+ struct rpc_cred __rcu *ro_cred;
+ struct rpc_cred __rcu *rw_cred;
atomic_t ref;
spinlock_t lock;
struct nfs4_ff_layoutstat read_stat;
@@ -154,6 +154,12 @@ ff_layout_no_fallback_to_mds(struct pnfs_layout_segment *lseg)
}
static inline bool
+ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
+{
+ return FF_LAYOUT_LSEG(lseg)->flags & FF_FLAGS_NO_READ_IO;
+}
+
+static inline bool
ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
{
return nfs4_test_deviceid_unavailable(node);
@@ -192,4 +198,7 @@ nfs4_ff_find_or_create_ds_client(struct pnfs_layout_segment *lseg,
struct rpc_cred *ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg,
u32 ds_idx, struct rpc_cred *mdscred);
bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg);
+bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg);
+bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg);
+
#endif /* FS_NFS_NFS4FLEXFILELAYOUT_H */
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index add0e5a70..0aa36be71 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -228,7 +228,8 @@ ff_ds_error_match(const struct nfs4_ff_layout_ds_err *e1,
return e1->opnum < e2->opnum ? -1 : 1;
if (e1->status != e2->status)
return e1->status < e2->status ? -1 : 1;
- ret = memcmp(&e1->stateid, &e2->stateid, sizeof(e1->stateid));
+ ret = memcmp(e1->stateid.data, e2->stateid.data,
+ sizeof(e1->stateid.data));
if (ret != 0)
return ret;
ret = memcmp(&e1->deviceid, &e2->deviceid, sizeof(e1->deviceid));
@@ -302,40 +303,26 @@ int ff_layout_track_ds_error(struct nfs4_flexfile_layout *flo,
return 0;
}
-/* currently we only support AUTH_NONE and AUTH_SYS */
-static rpc_authflavor_t
-nfs4_ff_layout_choose_authflavor(struct nfs4_ff_layout_mirror *mirror)
+static struct rpc_cred *
+ff_layout_get_mirror_cred(struct nfs4_ff_layout_mirror *mirror, u32 iomode)
{
- if (mirror->uid == (u32)-1)
- return RPC_AUTH_NULL;
- return RPC_AUTH_UNIX;
-}
+ struct rpc_cred *cred, __rcu **pcred;
-/* fetch cred for NFSv3 DS */
-static int ff_layout_update_mirror_cred(struct nfs4_ff_layout_mirror *mirror,
- struct nfs4_pnfs_ds *ds)
-{
- if (ds->ds_clp && !mirror->cred &&
- mirror->mirror_ds->ds_versions[0].version == 3) {
- struct rpc_auth *auth = ds->ds_clp->cl_rpcclient->cl_auth;
- struct rpc_cred *cred;
- struct auth_cred acred = {
- .uid = make_kuid(&init_user_ns, mirror->uid),
- .gid = make_kgid(&init_user_ns, mirror->gid),
- };
-
- /* AUTH_NULL ignores acred */
- cred = auth->au_ops->lookup_cred(auth, &acred, 0);
- if (IS_ERR(cred)) {
- dprintk("%s: lookup_cred failed with %ld\n",
- __func__, PTR_ERR(cred));
- return PTR_ERR(cred);
- } else {
- if (cmpxchg(&mirror->cred, NULL, cred))
- put_rpccred(cred);
- }
- }
- return 0;
+ if (iomode == IOMODE_READ)
+ pcred = &mirror->ro_cred;
+ else
+ pcred = &mirror->rw_cred;
+
+ rcu_read_lock();
+ do {
+ cred = rcu_dereference(*pcred);
+ if (!cred)
+ break;
+
+ cred = get_rpccred_rcu(cred);
+ } while(!cred);
+ rcu_read_unlock();
+ return cred;
}
struct nfs_fh *
@@ -356,7 +343,23 @@ out:
return fh;
}
-/* Upon return, either ds is connected, or ds is NULL */
+/**
+ * nfs4_ff_layout_prepare_ds - prepare a DS connection for an RPC call
+ * @lseg: the layout segment we're operating on
+ * @ds_idx: index of the DS to use
+ * @fail_return: return layout on connect failure?
+ *
+ * Try to prepare a DS connection to accept an RPC call. This involves
+ * selecting a mirror to use and connecting the client to it if it's not
+ * already connected.
+ *
+ * Since we only need a single functioning mirror to satisfy a read, we don't
+ * want to return the layout if there is one. For writes though, any down
+ * mirror should result in a LAYOUTRETURN. @fail_return is how we distinguish
+ * between the two cases.
+ *
+ * Returns a pointer to a connected DS object on success or NULL on failure.
+ */
struct nfs4_pnfs_ds *
nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
bool fail_return)
@@ -367,7 +370,6 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct inode *ino = lseg->pls_layout->plh_inode;
struct nfs_server *s = NFS_SERVER(ino);
unsigned int max_payload;
- rpc_authflavor_t flavor;
if (!ff_layout_mirror_valid(lseg, mirror)) {
pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
@@ -383,9 +385,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
/* matching smp_wmb() in _nfs4_pnfs_v3/4_ds_connect */
smp_rmb();
if (ds->ds_clp)
- goto out_update_creds;
-
- flavor = nfs4_ff_layout_choose_authflavor(mirror);
+ goto out;
/* FIXME: For now we assume the server sent only one version of NFS
* to use for the DS.
@@ -394,7 +394,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
dataserver_retrans,
mirror->mirror_ds->ds_versions[0].version,
mirror->mirror_ds->ds_versions[0].minor_version,
- flavor);
+ RPC_AUTH_UNIX);
/* connect success, check rsize/wsize limit */
if (ds->ds_clp) {
@@ -410,20 +410,10 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
mirror, lseg->pls_range.offset,
lseg->pls_range.length, NFS4ERR_NXIO,
OP_ILLEGAL, GFP_NOIO);
- if (!fail_return) {
- if (ff_layout_has_available_ds(lseg))
- set_bit(NFS_LAYOUT_RETURN_REQUESTED,
- &lseg->pls_layout->plh_flags);
- else
- pnfs_error_mark_layout_for_return(ino, lseg);
- } else
+ if (fail_return || !ff_layout_has_available_ds(lseg))
pnfs_error_mark_layout_for_return(ino, lseg);
ds = NULL;
- goto out;
}
-out_update_creds:
- if (ff_layout_update_mirror_cred(mirror, ds))
- ds = NULL;
out:
return ds;
}
@@ -433,16 +423,15 @@ ff_layout_get_ds_cred(struct pnfs_layout_segment *lseg, u32 ds_idx,
struct rpc_cred *mdscred)
{
struct nfs4_ff_layout_mirror *mirror = FF_LAYOUT_COMP(lseg, ds_idx);
- struct rpc_cred *cred = ERR_PTR(-EINVAL);
-
- if (!nfs4_ff_layout_prepare_ds(lseg, ds_idx, true))
- goto out;
+ struct rpc_cred *cred;
- if (mirror && mirror->cred)
- cred = mirror->cred;
- else
- cred = mdscred;
-out:
+ if (mirror) {
+ cred = ff_layout_get_mirror_cred(mirror, lseg->pls_range.iomode);
+ if (!cred)
+ cred = get_rpccred(mdscred);
+ } else {
+ cred = get_rpccred(mdscred);
+ }
return cred;
}
@@ -562,6 +551,18 @@ bool ff_layout_has_available_ds(struct pnfs_layout_segment *lseg)
return ff_rw_layout_has_available_ds(lseg);
}
+bool ff_layout_avoid_mds_available_ds(struct pnfs_layout_segment *lseg)
+{
+ return ff_layout_no_fallback_to_mds(lseg) ||
+ ff_layout_has_available_ds(lseg);
+}
+
+bool ff_layout_avoid_read_on_rw(struct pnfs_layout_segment *lseg)
+{
+ return lseg->pls_range.iomode == IOMODE_RW &&
+ ff_layout_no_read_on_rw(lseg);
+}
+
module_param(dataserver_retrans, uint, 0644);
MODULE_PARM_DESC(dataserver_retrans, "The number of times the NFSv4.1 client "
"retries a request before it attempts further "
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 738c84a42..dda689d7a 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -282,6 +282,7 @@ nfs_init_locked(struct inode *inode, void *opaque)
struct nfs_fattr *fattr = desc->fattr;
set_nfs_fileid(inode, fattr->fileid);
+ inode->i_mode = fattr->mode;
nfs_copy_fh(NFS_FH(inode), desc->fh);
return 0;
}
@@ -1958,9 +1959,7 @@ static void init_once(void *foo)
nfsi->nrequests = 0;
nfsi->commit_info.ncommit = 0;
atomic_set(&nfsi->commit_info.rpcs_out, 0);
- atomic_set(&nfsi->silly_count, 1);
- INIT_HLIST_HEAD(&nfsi->silly_list);
- init_waitqueue_head(&nfsi->waitqueue);
+ init_rwsem(&nfsi->rmdir_sem);
nfs4_init_once(nfsi);
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index f1d1d2c47..5154fa65a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -477,6 +477,7 @@ void nfs_mark_request_commit(struct nfs_page *req,
u32 ds_commit_idx);
int nfs_write_need_commit(struct nfs_pgio_header *);
void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
+int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf);
int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
int how, struct nfs_commit_info *cinfo);
void nfs_retry_commit(struct list_head *page_list,
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 17c0fa1ec..720d92f5a 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -11,6 +11,38 @@
#define NFSDBG_FACILITY NFSDBG_PROC
+/*
+ * nfs3_prepare_get_acl, nfs3_complete_get_acl, nfs3_abort_get_acl: Helpers for
+ * caching get_acl results in a race-free way. See fs/posix_acl.c:get_acl()
+ * for explanations.
+ */
+static void nfs3_prepare_get_acl(struct posix_acl **p)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ if (cmpxchg(p, ACL_NOT_CACHED, sentinel) != ACL_NOT_CACHED) {
+ /* Not the first reader or sentinel already in place. */
+ }
+}
+
+static void nfs3_complete_get_acl(struct posix_acl **p, struct posix_acl *acl)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ /* Only cache the ACL if our sentinel is still in place. */
+ posix_acl_dup(acl);
+ if (cmpxchg(p, sentinel, acl) != sentinel)
+ posix_acl_release(acl);
+}
+
+static void nfs3_abort_get_acl(struct posix_acl **p)
+{
+ struct posix_acl *sentinel = uncached_acl_sentinel(current);
+
+ /* Remove our sentinel upon failure. */
+ cmpxchg(p, sentinel, ACL_NOT_CACHED);
+}
+
struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
{
struct nfs_server *server = NFS_SERVER(inode);
@@ -55,6 +87,11 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
if (res.fattr == NULL)
return ERR_PTR(-ENOMEM);
+ if (args.mask & NFS_ACL)
+ nfs3_prepare_get_acl(&inode->i_acl);
+ if (args.mask & NFS_DFACL)
+ nfs3_prepare_get_acl(&inode->i_default_acl);
+
status = rpc_call_sync(server->client_acl, &msg, 0);
dprintk("NFS reply getacl: %d\n", status);
@@ -89,12 +126,12 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
}
if (res.mask & NFS_ACL)
- set_cached_acl(inode, ACL_TYPE_ACCESS, res.acl_access);
+ nfs3_complete_get_acl(&inode->i_acl, res.acl_access);
else
forget_cached_acl(inode, ACL_TYPE_ACCESS);
if (res.mask & NFS_DFACL)
- set_cached_acl(inode, ACL_TYPE_DEFAULT, res.acl_default);
+ nfs3_complete_get_acl(&inode->i_default_acl, res.acl_default);
else
forget_cached_acl(inode, ACL_TYPE_DEFAULT);
@@ -108,6 +145,8 @@ struct posix_acl *nfs3_get_acl(struct inode *inode, int type)
}
getout:
+ nfs3_abort_get_acl(&inode->i_acl);
+ nfs3_abort_get_acl(&inode->i_default_acl);
posix_acl_release(res.acl_access);
posix_acl_release(res.acl_default);
nfs_free_fattr(res.fattr);
diff --git a/fs/nfs/nfs42.h b/fs/nfs/nfs42.h
index b587ccd31..b6cd15314 100644
--- a/fs/nfs/nfs42.h
+++ b/fs/nfs/nfs42.h
@@ -13,6 +13,7 @@
/* nfs4.2proc.c */
int nfs42_proc_allocate(struct file *, loff_t, loff_t);
+ssize_t nfs42_proc_copy(struct file *, loff_t, struct file *, loff_t, size_t);
int nfs42_proc_deallocate(struct file *, loff_t, loff_t);
loff_t nfs42_proc_llseek(struct file *, loff_t, int);
int nfs42_proc_layoutstats_generic(struct nfs_server *,
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index dff83460e..aa03ed09b 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -126,6 +126,111 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len)
return err;
}
+static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
+ struct nfs_lock_context *src_lock,
+ struct file *dst, loff_t pos_dst,
+ struct nfs_lock_context *dst_lock,
+ size_t count)
+{
+ struct nfs42_copy_args args = {
+ .src_fh = NFS_FH(file_inode(src)),
+ .src_pos = pos_src,
+ .dst_fh = NFS_FH(file_inode(dst)),
+ .dst_pos = pos_dst,
+ .count = count,
+ };
+ struct nfs42_copy_res res;
+ struct rpc_message msg = {
+ .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
+ .rpc_argp = &args,
+ .rpc_resp = &res,
+ };
+ struct inode *dst_inode = file_inode(dst);
+ struct nfs_server *server = NFS_SERVER(dst_inode);
+ int status;
+
+ status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+ src_lock, FMODE_READ);
+ if (status)
+ return status;
+
+ status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+ dst_lock, FMODE_WRITE);
+ if (status)
+ return status;
+
+ status = nfs4_call_sync(server->client, server, &msg,
+ &args.seq_args, &res.seq_res, 0);
+ if (status == -ENOTSUPP)
+ server->caps &= ~NFS_CAP_COPY;
+ if (status)
+ return status;
+
+ if (res.write_res.verifier.committed != NFS_FILE_SYNC) {
+ status = nfs_commit_file(dst, &res.write_res.verifier.verifier);
+ if (status)
+ return status;
+ }
+
+ truncate_pagecache_range(dst_inode, pos_dst,
+ pos_dst + res.write_res.count);
+
+ return res.write_res.count;
+}
+
+ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
+ struct file *dst, loff_t pos_dst,
+ size_t count)
+{
+ struct nfs_server *server = NFS_SERVER(file_inode(dst));
+ struct nfs_lock_context *src_lock;
+ struct nfs_lock_context *dst_lock;
+ struct nfs4_exception src_exception = { };
+ struct nfs4_exception dst_exception = { };
+ ssize_t err, err2;
+
+ if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
+ return -EOPNOTSUPP;
+
+ src_lock = nfs_get_lock_context(nfs_file_open_context(src));
+ if (IS_ERR(src_lock))
+ return PTR_ERR(src_lock);
+
+ src_exception.inode = file_inode(src);
+ src_exception.state = src_lock->open_context->state;
+
+ dst_lock = nfs_get_lock_context(nfs_file_open_context(dst));
+ if (IS_ERR(dst_lock)) {
+ err = PTR_ERR(dst_lock);
+ goto out_put_src_lock;
+ }
+
+ dst_exception.inode = file_inode(dst);
+ dst_exception.state = dst_lock->open_context->state;
+
+ do {
+ inode_lock(file_inode(dst));
+ err = _nfs42_proc_copy(src, pos_src, src_lock,
+ dst, pos_dst, dst_lock, count);
+ inode_unlock(file_inode(dst));
+
+ if (err == -ENOTSUPP) {
+ err = -EOPNOTSUPP;
+ break;
+ }
+
+ err2 = nfs4_handle_exception(server, err, &src_exception);
+ err = nfs4_handle_exception(server, err, &dst_exception);
+ if (!err)
+ err = err2;
+ } while (src_exception.retry || dst_exception.retry);
+
+ nfs_put_lock_context(dst_lock);
+out_put_src_lock:
+ nfs_put_lock_context(src_lock);
+ return err;
+}
+
static loff_t _nfs42_proc_llseek(struct file *filep,
struct nfs_lock_context *lock, loff_t offset, int whence)
{
@@ -232,7 +337,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
* with the current stateid.
*/
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
} else
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 0ca482a51..6dc6f2aea 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -9,9 +9,22 @@
#define encode_fallocate_maxsz (encode_stateid_maxsz + \
2 /* offset */ + \
2 /* length */)
+#define NFS42_WRITE_RES_SIZE (1 /* wr_callback_id size */ +\
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 2 /* wr_count */ + \
+ 1 /* wr_committed */ + \
+ XDR_QUADLEN(NFS4_VERIFIER_SIZE))
#define encode_allocate_maxsz (op_encode_hdr_maxsz + \
encode_fallocate_maxsz)
#define decode_allocate_maxsz (op_decode_hdr_maxsz)
+#define encode_copy_maxsz (op_encode_hdr_maxsz + \
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ XDR_QUADLEN(NFS4_STATEID_SIZE) + \
+ 2 + 2 + 2 + 1 + 1 + 1)
+#define decode_copy_maxsz (op_decode_hdr_maxsz + \
+ NFS42_WRITE_RES_SIZE + \
+ 1 /* cr_consecutive */ + \
+ 1 /* cr_synchronous */)
#define encode_deallocate_maxsz (op_encode_hdr_maxsz + \
encode_fallocate_maxsz)
#define decode_deallocate_maxsz (op_decode_hdr_maxsz)
@@ -49,6 +62,16 @@
decode_putfh_maxsz + \
decode_allocate_maxsz + \
decode_getattr_maxsz)
+#define NFS4_enc_copy_sz (compound_encode_hdr_maxsz + \
+ encode_putfh_maxsz + \
+ encode_savefh_maxsz + \
+ encode_putfh_maxsz + \
+ encode_copy_maxsz)
+#define NFS4_dec_copy_sz (compound_decode_hdr_maxsz + \
+ decode_putfh_maxsz + \
+ decode_savefh_maxsz + \
+ decode_putfh_maxsz + \
+ decode_copy_maxsz)
#define NFS4_enc_deallocate_sz (compound_encode_hdr_maxsz + \
encode_putfh_maxsz + \
encode_deallocate_maxsz + \
@@ -102,6 +125,23 @@ static void encode_allocate(struct xdr_stream *xdr,
encode_fallocate(xdr, args);
}
+static void encode_copy(struct xdr_stream *xdr,
+ struct nfs42_copy_args *args,
+ struct compound_hdr *hdr)
+{
+ encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr);
+ encode_nfs4_stateid(xdr, &args->src_stateid);
+ encode_nfs4_stateid(xdr, &args->dst_stateid);
+
+ encode_uint64(xdr, args->src_pos);
+ encode_uint64(xdr, args->dst_pos);
+ encode_uint64(xdr, args->count);
+
+ encode_uint32(xdr, 1); /* consecutive = true */
+ encode_uint32(xdr, 1); /* synchronous = true */
+ encode_uint32(xdr, 0); /* src server list */
+}
+
static void encode_deallocate(struct xdr_stream *xdr,
struct nfs42_falloc_args *args,
struct compound_hdr *hdr)
@@ -182,6 +222,26 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
}
/*
+ * Encode COPY request
+ */
+static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
+ struct xdr_stream *xdr,
+ struct nfs42_copy_args *args)
+{
+ struct compound_hdr hdr = {
+ .minorversion = nfs4_xdr_minorversion(&args->seq_args),
+ };
+
+ encode_compound_hdr(xdr, req, &hdr);
+ encode_sequence(xdr, &args->seq_args, &hdr);
+ encode_putfh(xdr, args->src_fh, &hdr);
+ encode_savefh(xdr, &hdr);
+ encode_putfh(xdr, args->dst_fh, &hdr);
+ encode_copy(xdr, args, &hdr);
+ encode_nops(&hdr);
+}
+
+/*
* Encode DEALLOCATE request
*/
static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
@@ -266,6 +326,62 @@ static int decode_allocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
return decode_op_hdr(xdr, OP_ALLOCATE);
}
+static int decode_write_response(struct xdr_stream *xdr,
+ struct nfs42_write_res *res)
+{
+ __be32 *p;
+ int stateids;
+
+ p = xdr_inline_decode(xdr, 4 + 8 + 4);
+ if (unlikely(!p))
+ goto out_overflow;
+
+ stateids = be32_to_cpup(p++);
+ p = xdr_decode_hyper(p, &res->count);
+ res->verifier.committed = be32_to_cpup(p);
+ return decode_verifier(xdr, &res->verifier.verifier);
+
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
+static int decode_copy_requirements(struct xdr_stream *xdr,
+ struct nfs42_copy_res *res) {
+ __be32 *p;
+
+ p = xdr_inline_decode(xdr, 4 + 4);
+ if (unlikely(!p))
+ goto out_overflow;
+
+ res->consecutive = be32_to_cpup(p++);
+ res->synchronous = be32_to_cpup(p++);
+ return 0;
+out_overflow:
+ print_overflow_msg(__func__, xdr);
+ return -EIO;
+}
+
+static int decode_copy(struct xdr_stream *xdr, struct nfs42_copy_res *res)
+{
+ int status;
+
+ status = decode_op_hdr(xdr, OP_COPY);
+ if (status == NFS4ERR_OFFLOAD_NO_REQS) {
+ status = decode_copy_requirements(xdr, res);
+ if (status)
+ return status;
+ return NFS4ERR_OFFLOAD_NO_REQS;
+ } else if (status)
+ return status;
+
+ status = decode_write_response(xdr, &res->write_res);
+ if (status)
+ return status;
+
+ return decode_copy_requirements(xdr, res);
+}
+
static int decode_deallocate(struct xdr_stream *xdr, struct nfs42_falloc_res *res)
{
return decode_op_hdr(xdr, OP_DEALLOCATE);
@@ -331,6 +447,36 @@ out:
}
/*
+ * Decode COPY response
+ */
+static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
+ struct xdr_stream *xdr,
+ struct nfs42_copy_res *res)
+{
+ struct compound_hdr hdr;
+ int status;
+
+ status = decode_compound_hdr(xdr, &hdr);
+ if (status)
+ goto out;
+ status = decode_sequence(xdr, &res->seq_res, rqstp);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_savefh(xdr);
+ if (status)
+ goto out;
+ status = decode_putfh(xdr);
+ if (status)
+ goto out;
+ status = decode_copy(xdr, res);
+out:
+ return status;
+}
+
+/*
* Decode DEALLOCATE request
*/
static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 4afdee420..768456fa1 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -438,8 +438,9 @@ extern void nfs41_handle_server_scope(struct nfs_client *,
struct nfs41_server_scope **);
extern void nfs4_put_lock_state(struct nfs4_lock_state *lsp);
extern int nfs4_set_lock_state(struct nfs4_state *state, struct file_lock *fl);
-extern int nfs4_select_rw_stateid(nfs4_stateid *, struct nfs4_state *,
- fmode_t, const struct nfs_lockowner *);
+extern int nfs4_select_rw_stateid(struct nfs4_state *, fmode_t,
+ const struct nfs_lockowner *, nfs4_stateid *,
+ struct rpc_cred **);
extern struct nfs_seqid *nfs_alloc_seqid(struct nfs_seqid_counter *counter, gfp_t gfp_mask);
extern int nfs_wait_on_sequence(struct nfs_seqid *seqid, struct rpc_task *task);
@@ -496,12 +497,15 @@ extern struct svc_version nfs4_callback_version4;
static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
{
- memcpy(dst, src, sizeof(*dst));
+ memcpy(dst->data, src->data, sizeof(dst->data));
+ dst->type = src->type;
}
static inline bool nfs4_stateid_match(const nfs4_stateid *dst, const nfs4_stateid *src)
{
- return memcmp(dst, src, sizeof(*dst)) == 0;
+ if (dst->type != src->type)
+ return false;
+ return memcmp(dst->data, src->data, sizeof(dst->data)) == 0;
}
static inline bool nfs4_stateid_match_other(const nfs4_stateid *dst, const nfs4_stateid *src)
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index d03905164..014b0e41a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -129,6 +129,28 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
}
#ifdef CONFIG_NFS_V4_2
+static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ size_t count, unsigned int flags)
+{
+ struct inode *in_inode = file_inode(file_in);
+ struct inode *out_inode = file_inode(file_out);
+ int ret;
+
+ if (in_inode == out_inode)
+ return -EINVAL;
+
+ /* flush any pending writes */
+ ret = nfs_sync_inode(in_inode);
+ if (ret)
+ return ret;
+ ret = nfs_sync_inode(out_inode);
+ if (ret)
+ return ret;
+
+ return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
+}
+
static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
{
loff_t ret;
@@ -243,6 +265,7 @@ const struct file_operations nfs4_file_operations = {
.check_flags = nfs_check_flags,
.setlease = simple_nosetlease,
#ifdef CONFIG_NFS_V4_2
+ .copy_file_range = nfs4_copy_file_range,
.llseek = nfs4_file_llseek,
.fallocate = nfs42_fallocate,
.clone_file_range = nfs42_clone_file_range,
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 5ba22c6b0..c444285bb 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -201,7 +201,7 @@ int nfs_idmap_init(void)
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, cred,
(KEY_POS_ALL & ~KEY_POS_SETATTR) |
KEY_USR_VIEW | KEY_USR_READ,
- KEY_ALLOC_NOT_IN_QUOTA, NULL);
+ KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
if (IS_ERR(keyring)) {
ret = PTR_ERR(keyring);
goto failed_put_cred;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index de2523f5e..ff416d0e2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -74,6 +74,17 @@
#define NFS4_POLL_RETRY_MIN (HZ/10)
#define NFS4_POLL_RETRY_MAX (15*HZ)
+/* file attributes which can be mapped to nfs attributes */
+#define NFS4_VALID_ATTRS (ATTR_MODE \
+ | ATTR_UID \
+ | ATTR_GID \
+ | ATTR_SIZE \
+ | ATTR_ATIME \
+ | ATTR_MTIME \
+ | ATTR_CTIME \
+ | ATTR_ATIME_SET \
+ | ATTR_MTIME_SET)
+
struct nfs4_opendata;
static int _nfs4_proc_open(struct nfs4_opendata *data);
static int _nfs4_recover_proc_open(struct nfs4_opendata *data);
@@ -416,6 +427,7 @@ static int nfs4_do_handle_exception(struct nfs_server *server,
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
case -NFS4ERR_GRACE:
+ case -NFS4ERR_RECALLCONFLICT:
exception->delay = 1;
return 0;
@@ -2558,15 +2570,20 @@ static int _nfs4_do_open(struct inode *dir,
if ((opendata->o_arg.open_flags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL) &&
(opendata->o_arg.createmode != NFS4_CREATE_GUARDED)) {
nfs4_exclusive_attrset(opendata, sattr, &label);
-
- nfs_fattr_init(opendata->o_res.f_attr);
- status = nfs4_do_setattr(state->inode, cred,
- opendata->o_res.f_attr, sattr,
- state, label, olabel);
- if (status == 0) {
- nfs_setattr_update_inode(state->inode, sattr,
- opendata->o_res.f_attr);
- nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
+ /*
+ * send create attributes which was not set by open
+ * with an extra setattr.
+ */
+ if (sattr->ia_valid & NFS4_VALID_ATTRS) {
+ nfs_fattr_init(opendata->o_res.f_attr);
+ status = nfs4_do_setattr(state->inode, cred,
+ opendata->o_res.f_attr, sattr,
+ state, label, olabel);
+ if (status == 0) {
+ nfs_setattr_update_inode(state->inode, sattr,
+ opendata->o_res.f_attr);
+ nfs_setsecurity(state->inode, opendata->o_res.f_attr, olabel);
+ }
}
}
if (opened && opendata->file_created)
@@ -2676,6 +2693,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
.rpc_resp = &res,
.rpc_cred = cred,
};
+ struct rpc_cred *delegation_cred = NULL;
unsigned long timestamp = jiffies;
fmode_t fmode;
bool truncate;
@@ -2691,7 +2709,7 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
truncate = (sattr->ia_valid & ATTR_SIZE) ? true : false;
fmode = truncate ? FMODE_WRITE : FMODE_READ;
- if (nfs4_copy_delegation_stateid(&arg.stateid, inode, fmode)) {
+ if (nfs4_copy_delegation_stateid(inode, fmode, &arg.stateid, &delegation_cred)) {
/* Use that stateid */
} else if (truncate && state != NULL) {
struct nfs_lockowner lockowner = {
@@ -2700,13 +2718,17 @@ static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
};
if (!nfs4_valid_open_stateid(state))
return -EBADF;
- if (nfs4_select_rw_stateid(&arg.stateid, state, FMODE_WRITE,
- &lockowner) == -EIO)
+ if (nfs4_select_rw_stateid(state, FMODE_WRITE, &lockowner,
+ &arg.stateid, &delegation_cred) == -EIO)
return -EBADF;
} else
nfs4_stateid_copy(&arg.stateid, &zero_stateid);
+ if (delegation_cred)
+ msg.rpc_cred = delegation_cred;
status = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1);
+
+ put_rpccred(delegation_cred);
if (status == 0 && state != NULL)
renew_lease(server, timestamp);
trace_nfs4_setattr(inode, &arg.stateid, status);
@@ -3776,7 +3798,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
{
- nfs4_setup_sequence(NFS_SERVER(data->dir),
+ nfs4_setup_sequence(NFS_SB(data->dentry->d_sb),
&data->args.seq_args,
&data->res.seq_res,
task);
@@ -4284,7 +4306,7 @@ int nfs4_set_rw_stateid(nfs4_stateid *stateid,
if (l_ctx != NULL)
lockowner = &l_ctx->lockowner;
- return nfs4_select_rw_stateid(stateid, ctx->state, fmode, lockowner);
+ return nfs4_select_rw_stateid(ctx->state, fmode, lockowner, stateid, NULL);
}
EXPORT_SYMBOL_GPL(nfs4_set_rw_stateid);
@@ -4992,12 +5014,11 @@ static int nfs4_do_set_security_label(struct inode *inode,
}
static int
-nfs4_set_security_label(struct dentry *dentry, const void *buf, size_t buflen)
+nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen)
{
struct nfs4_label ilabel, *olabel = NULL;
struct nfs_fattr fattr;
struct rpc_cred *cred;
- struct inode *inode = d_inode(dentry);
int status;
if (!nfs_server_capable(inode, NFS_CAP_SECURITY_LABEL))
@@ -6053,6 +6074,7 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
struct nfs_inode *nfsi = NFS_I(state->inode);
+ struct nfs4_state_owner *sp = state->owner;
unsigned char fl_flags = request->fl_flags;
int status = -ENOLCK;
@@ -6067,6 +6089,7 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
status = do_vfs_lock(state->inode, request);
if (status < 0)
goto out;
+ mutex_lock(&sp->so_delegreturn_mutex);
down_read(&nfsi->rwsem);
if (test_bit(NFS_DELEGATED_STATE, &state->flags)) {
/* Yes: cache locks! */
@@ -6074,9 +6097,11 @@ static int _nfs4_proc_setlk(struct nfs4_state *state, int cmd, struct file_lock
request->fl_flags = fl_flags & ~FL_SLEEP;
status = do_vfs_lock(state->inode, request);
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
goto out;
}
up_read(&nfsi->rwsem);
+ mutex_unlock(&sp->so_delegreturn_mutex);
status = _nfs4_do_setlk(state, cmd, request, NFS_LOCK_NEW);
out:
request->fl_flags = fl_flags;
@@ -6254,18 +6279,18 @@ nfs4_release_lockowner(struct nfs_server *server, struct nfs4_lock_state *lsp)
#define XATTR_NAME_NFSV4_ACL "system.nfs4_acl"
static int nfs4_xattr_set_nfs4_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- const void *buf, size_t buflen,
- int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
{
- return nfs4_proc_set_acl(d_inode(dentry), buf, buflen);
+ return nfs4_proc_set_acl(inode, buf, buflen);
}
static int nfs4_xattr_get_nfs4_acl(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- void *buf, size_t buflen)
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
{
- return nfs4_proc_get_acl(d_inode(dentry), buf, buflen);
+ return nfs4_proc_get_acl(inode, buf, buflen);
}
static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
@@ -6276,22 +6301,22 @@ static bool nfs4_xattr_list_nfs4_acl(struct dentry *dentry)
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
static int nfs4_xattr_set_nfs4_label(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- const void *buf, size_t buflen,
- int flags)
+ struct dentry *unused, struct inode *inode,
+ const char *key, const void *buf,
+ size_t buflen, int flags)
{
if (security_ismaclabel(key))
- return nfs4_set_security_label(dentry, buf, buflen);
+ return nfs4_set_security_label(inode, buf, buflen);
return -EOPNOTSUPP;
}
static int nfs4_xattr_get_nfs4_label(const struct xattr_handler *handler,
- struct dentry *dentry, const char *key,
- void *buf, size_t buflen)
+ struct dentry *unused, struct inode *inode,
+ const char *key, void *buf, size_t buflen)
{
if (security_ismaclabel(key))
- return nfs4_get_security_label(d_inode(dentry), buf, buflen);
+ return nfs4_get_security_label(inode, buf, buflen);
return -EOPNOTSUPP;
}
@@ -7350,9 +7375,11 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
* always set csa_cachethis to FALSE because the current implementation
* of the back channel DRC only supports caching the CB_SEQUENCE operation.
*/
-static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
+static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args,
+ struct rpc_clnt *clnt)
{
unsigned int max_rqst_sz, max_resp_sz;
+ unsigned int max_bc_payload = rpc_max_bc_payload(clnt);
max_rqst_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxwrite_overhead;
max_resp_sz = NFS_MAX_FILE_IO_SIZE + nfs41_maxread_overhead;
@@ -7370,8 +7397,8 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args)
args->fc_attrs.max_ops, args->fc_attrs.max_reqs);
/* Back channel attributes */
- args->bc_attrs.max_rqst_sz = PAGE_SIZE;
- args->bc_attrs.max_resp_sz = PAGE_SIZE;
+ args->bc_attrs.max_rqst_sz = max_bc_payload;
+ args->bc_attrs.max_resp_sz = max_bc_payload;
args->bc_attrs.max_resp_sz_cached = 0;
args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
@@ -7475,7 +7502,7 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
};
int status;
- nfs4_init_channel_attrs(&args);
+ nfs4_init_channel_attrs(&args, clp->cl_rpcclient);
args.flags = (SESSION4_PERSIST | SESSION4_BACK_CHAN);
status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
@@ -7819,40 +7846,34 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
struct nfs4_layoutget *lgp = calldata;
struct nfs_server *server = NFS_SERVER(lgp->args.inode);
struct nfs4_session *session = nfs4_get_session(server);
- int ret;
dprintk("--> %s\n", __func__);
- /* Note the is a race here, where a CB_LAYOUTRECALL can come in
- * right now covering the LAYOUTGET we are about to send.
- * However, that is not so catastrophic, and there seems
- * to be no way to prevent it completely.
- */
- if (nfs41_setup_sequence(session, &lgp->args.seq_args,
- &lgp->res.seq_res, task))
- return;
- ret = pnfs_choose_layoutget_stateid(&lgp->args.stateid,
- NFS_I(lgp->args.inode)->layout,
- &lgp->args.range,
- lgp->args.ctx->state);
- if (ret < 0)
- rpc_exit(task, ret);
+ nfs41_setup_sequence(session, &lgp->args.seq_args,
+ &lgp->res.seq_res, task);
+ dprintk("<-- %s\n", __func__);
}
static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
{
struct nfs4_layoutget *lgp = calldata;
+
+ dprintk("--> %s\n", __func__);
+ nfs41_sequence_done(task, &lgp->res.seq_res);
+ dprintk("<-- %s\n", __func__);
+}
+
+static int
+nfs4_layoutget_handle_exception(struct rpc_task *task,
+ struct nfs4_layoutget *lgp, struct nfs4_exception *exception)
+{
struct inode *inode = lgp->args.inode;
struct nfs_server *server = NFS_SERVER(inode);
struct pnfs_layout_hdr *lo;
- struct nfs4_state *state = NULL;
- unsigned long timeo, now, giveup;
+ int status = task->tk_status;
dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
- if (!nfs41_sequence_done(task, &lgp->res.seq_res))
- goto out;
-
- switch (task->tk_status) {
+ switch (status) {
case 0:
goto out;
@@ -7862,62 +7883,48 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
* retry go inband.
*/
case -NFS4ERR_LAYOUTUNAVAILABLE:
- task->tk_status = -ENODATA;
+ status = -ENODATA;
goto out;
/*
* NFS4ERR_BADLAYOUT means the MDS cannot return a layout of
* length lgp->args.minlength != 0 (see RFC5661 section 18.43.3).
*/
case -NFS4ERR_BADLAYOUT:
- goto out_overflow;
+ status = -EOVERFLOW;
+ goto out;
/*
* NFS4ERR_LAYOUTTRYLATER is a conflict with another client
* (or clients) writing to the same RAID stripe except when
* the minlength argument is 0 (see RFC5661 section 18.43.3).
+ *
+ * Treat it like we would RECALLCONFLICT -- we retry for a little
+ * while, and then eventually give up.
*/
case -NFS4ERR_LAYOUTTRYLATER:
- if (lgp->args.minlength == 0)
- goto out_overflow;
- /*
- * NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
- * existing layout before getting a new one).
- */
- case -NFS4ERR_RECALLCONFLICT:
- timeo = rpc_get_timeout(task->tk_client);
- giveup = lgp->args.timestamp + timeo;
- now = jiffies;
- if (time_after(giveup, now)) {
- unsigned long delay;
-
- /* Delay for:
- * - Not less then NFS4_POLL_RETRY_MIN.
- * - One last time a jiffie before we give up
- * - exponential backoff (time_now minus start_attempt)
- */
- delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
- min((giveup - now - 1),
- now - lgp->args.timestamp));
-
- dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
- __func__, delay);
- rpc_delay(task, delay);
- /* Do not call nfs4_async_handle_error() */
- goto out_restart;
+ if (lgp->args.minlength == 0) {
+ status = -EOVERFLOW;
+ goto out;
}
- break;
+ /* Fallthrough */
+ case -NFS4ERR_RECALLCONFLICT:
+ nfs4_handle_exception(server, -NFS4ERR_RECALLCONFLICT,
+ exception);
+ status = -ERECALLCONFLICT;
+ goto out;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
+ exception->timeout = 0;
spin_lock(&inode->i_lock);
if (nfs4_stateid_match(&lgp->args.stateid,
&lgp->args.ctx->state->stateid)) {
spin_unlock(&inode->i_lock);
/* If the open stateid was bad, then recover it. */
- state = lgp->args.ctx->state;
+ exception->state = lgp->args.ctx->state;
break;
}
lo = NFS_I(inode)->layout;
- if (lo && nfs4_stateid_match(&lgp->args.stateid,
- &lo->plh_stateid)) {
+ if (lo && !test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) &&
+ nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
LIST_HEAD(head);
/*
@@ -7925,25 +7932,21 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
* with the current stateid.
*/
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- pnfs_mark_matching_lsegs_invalid(lo, &head, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, NULL, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
+ status = -EAGAIN;
+ goto out;
} else
spin_unlock(&inode->i_lock);
- goto out_restart;
}
- if (nfs4_async_handle_error(task, server, state, &lgp->timeout) == -EAGAIN)
- goto out_restart;
+
+ status = nfs4_handle_exception(server, status, exception);
+ if (exception->retry)
+ status = -EAGAIN;
out:
dprintk("<-- %s\n", __func__);
- return;
-out_restart:
- task->tk_status = 0;
- rpc_restart_call_prepare(task);
- return;
-out_overflow:
- task->tk_status = -EOVERFLOW;
- goto out;
+ return status;
}
static size_t max_response_pages(struct nfs_server *server)
@@ -8012,7 +8015,7 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = {
};
struct pnfs_layout_segment *
-nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
+nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
{
struct inode *inode = lgp->args.inode;
struct nfs_server *server = NFS_SERVER(inode);
@@ -8032,6 +8035,10 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
.flags = RPC_TASK_ASYNC,
};
struct pnfs_layout_segment *lseg = NULL;
+ struct nfs4_exception exception = {
+ .inode = inode,
+ .timeout = *timeout,
+ };
int status = 0;
dprintk("--> %s\n", __func__);
@@ -8045,7 +8052,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
return ERR_PTR(-ENOMEM);
}
lgp->args.layout.pglen = max_pages * PAGE_SIZE;
- lgp->args.timestamp = jiffies;
lgp->res.layoutp = &lgp->args.layout;
lgp->res.seq_res.sr_slot = NULL;
@@ -8055,13 +8061,17 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags)
if (IS_ERR(task))
return ERR_CAST(task);
status = nfs4_wait_for_completion_rpc_task(task);
- if (status == 0)
- status = task->tk_status;
+ if (status == 0) {
+ status = nfs4_layoutget_handle_exception(task, lgp, &exception);
+ *timeout = exception.timeout;
+ }
+
trace_nfs4_layoutget(lgp->args.ctx,
&lgp->args.range,
&lgp->res.range,
&lgp->res.stateid,
status);
+
/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
if (status == 0 && lgp->res.layoutp->len)
lseg = pnfs_layout_process(lgp);
@@ -8117,7 +8127,8 @@ static void nfs4_layoutreturn_release(void *calldata)
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
- pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range,
+ be32_to_cpu(lrp->args.stateid.seqid));
pnfs_mark_layout_returned_if_empty(lo);
if (lrp->res.lrs_present)
pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
@@ -8652,6 +8663,9 @@ nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
static bool nfs41_match_stateid(const nfs4_stateid *s1,
const nfs4_stateid *s2)
{
+ if (s1->type != s2->type)
+ return false;
+
if (memcmp(s1->other, s2->other, sizeof(s1->other)) != 0)
return false;
@@ -8792,6 +8806,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
| NFS_CAP_STATEID_NFSV41
| NFS_CAP_ATOMIC_OPEN_V1
| NFS_CAP_ALLOCATE
+ | NFS_CAP_COPY
| NFS_CAP_DEALLOCATE
| NFS_CAP_SEEK
| NFS_CAP_LAYOUTSTATS
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index d854693a1..834b87590 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -65,7 +65,10 @@
#define OPENOWNER_POOL_SIZE 8
-const nfs4_stateid zero_stateid;
+const nfs4_stateid zero_stateid = {
+ { .data = { 0 } },
+ .type = NFS4_SPECIAL_STATEID_TYPE,
+};
static DEFINE_MUTEX(nfs_clid_init_mutex);
int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
@@ -985,15 +988,20 @@ static void nfs4_copy_open_stateid(nfs4_stateid *dst, struct nfs4_state *state)
* Byte-range lock aware utility to initialize the stateid of read/write
* requests.
*/
-int nfs4_select_rw_stateid(nfs4_stateid *dst, struct nfs4_state *state,
- fmode_t fmode, const struct nfs_lockowner *lockowner)
+int nfs4_select_rw_stateid(struct nfs4_state *state,
+ fmode_t fmode, const struct nfs_lockowner *lockowner,
+ nfs4_stateid *dst, struct rpc_cred **cred)
{
- int ret = nfs4_copy_lock_stateid(dst, state, lockowner);
+ int ret;
+
+ if (cred != NULL)
+ *cred = NULL;
+ ret = nfs4_copy_lock_stateid(dst, state, lockowner);
if (ret == -EIO)
/* A lost lock - don't even consider delegations */
goto out;
/* returns true if delegation stateid found and copied */
- if (nfs4_copy_delegation_stateid(dst, state->inode, fmode)) {
+ if (nfs4_copy_delegation_stateid(state->inode, fmode, dst, cred)) {
ret = 0;
goto out;
}
@@ -1480,9 +1488,9 @@ restart:
}
spin_unlock(&state->state_lock);
}
- nfs4_put_open_state(state);
clear_bit(NFS_STATE_RECLAIM_NOGRACE,
&state->flags);
+ nfs4_put_open_state(state);
spin_lock(&sp->so_lock);
goto restart;
}
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 2c8d05dae..9c150b153 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1520,6 +1520,8 @@ DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
{ PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \
{ PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \
{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \
+ { PNFS_UPDATE_LAYOUT_INVALID_OPEN, "invalid open" }, \
+ { PNFS_UPDATE_LAYOUT_RETRY, "retrying" }, \
{ PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
TRACE_EVENT(pnfs_update_layout,
@@ -1528,9 +1530,10 @@ TRACE_EVENT(pnfs_update_layout,
u64 count,
enum pnfs_iomode iomode,
struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg,
enum pnfs_update_layout_reason reason
),
- TP_ARGS(inode, pos, count, iomode, lo, reason),
+ TP_ARGS(inode, pos, count, iomode, lo, lseg, reason),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(u64, fileid)
@@ -1540,6 +1543,7 @@ TRACE_EVENT(pnfs_update_layout,
__field(enum pnfs_iomode, iomode)
__field(int, layoutstateid_seq)
__field(u32, layoutstateid_hash)
+ __field(long, lseg)
__field(enum pnfs_update_layout_reason, reason)
),
TP_fast_assign(
@@ -1559,11 +1563,12 @@ TRACE_EVENT(pnfs_update_layout,
__entry->layoutstateid_seq = 0;
__entry->layoutstateid_hash = 0;
}
+ __entry->lseg = (long)lseg;
),
TP_printk(
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"iomode=%s pos=%llu count=%llu "
- "layoutstateid=%d:0x%08x (%s)",
+ "layoutstateid=%d:0x%08x lseg=0x%lx (%s)",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1571,6 +1576,7 @@ TRACE_EVENT(pnfs_update_layout,
(unsigned long long)__entry->pos,
(unsigned long long)__entry->count,
__entry->layoutstateid_seq, __entry->layoutstateid_hash,
+ __entry->lseg,
show_pnfs_update_layout_reason(__entry->reason)
)
);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 88474a4fc..661e753fe 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4270,6 +4270,24 @@ static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
return decode_opaque_fixed(xdr, stateid, NFS4_STATEID_SIZE);
}
+static int decode_open_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_OPEN_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
+static int decode_lock_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LOCK_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
+static int decode_delegation_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_DELEGATION_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
{
int status;
@@ -4278,7 +4296,7 @@ static int decode_close(struct xdr_stream *xdr, struct nfs_closeres *res)
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -4937,7 +4955,7 @@ static int decode_lock(struct xdr_stream *xdr, struct nfs_lock_res *res)
if (status == -EIO)
goto out;
if (status == 0) {
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_lock_stateid(xdr, &res->stateid);
if (unlikely(status))
goto out;
} else if (status == -NFS4ERR_DENIED)
@@ -4966,7 +4984,7 @@ static int decode_locku(struct xdr_stream *xdr, struct nfs_locku_res *res)
if (status != -EIO)
nfs_increment_lock_seqid(status, res->seqid);
if (status == 0)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_lock_stateid(xdr, &res->stateid);
return status;
}
@@ -5016,7 +5034,7 @@ static int decode_rw_delegation(struct xdr_stream *xdr,
__be32 *p;
int status;
- status = decode_stateid(xdr, &res->delegation);
+ status = decode_delegation_stateid(xdr, &res->delegation);
if (unlikely(status))
return status;
p = xdr_inline_decode(xdr, 4);
@@ -5096,7 +5114,7 @@ static int decode_open(struct xdr_stream *xdr, struct nfs_openres *res)
nfs_increment_open_seqid(status, res->seqid);
if (status)
return status;
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
if (unlikely(status))
return status;
@@ -5136,7 +5154,7 @@ static int decode_open_confirm(struct xdr_stream *xdr, struct nfs_open_confirmre
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -5148,7 +5166,7 @@ static int decode_open_downgrade(struct xdr_stream *xdr, struct nfs_closeres *re
if (status != -EIO)
nfs_increment_open_seqid(status, res->seqid);
if (!status)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_open_stateid(xdr, &res->stateid);
return status;
}
@@ -5838,6 +5856,12 @@ out_overflow:
}
#if defined(CONFIG_NFS_V4_1)
+static int decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
+{
+ stateid->type = NFS4_LAYOUT_STATEID_TYPE;
+ return decode_stateid(xdr, stateid);
+}
+
static int decode_getdeviceinfo(struct xdr_stream *xdr,
struct nfs4_getdeviceinfo_res *res)
{
@@ -5919,7 +5943,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
if (unlikely(!p))
goto out_overflow;
res->return_on_close = be32_to_cpup(p);
- decode_stateid(xdr, &res->stateid);
+ decode_layout_stateid(xdr, &res->stateid);
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
@@ -5985,7 +6009,7 @@ static int decode_layoutreturn(struct xdr_stream *xdr,
goto out_overflow;
res->lrs_present = be32_to_cpup(p);
if (res->lrs_present)
- status = decode_stateid(xdr, &res->stateid);
+ status = decode_layout_stateid(xdr, &res->stateid);
return status;
out_overflow:
print_overflow_msg(__func__, xdr);
@@ -7515,6 +7539,7 @@ struct rpc_procinfo nfs4_procedures[] = {
PROC(DEALLOCATE, enc_deallocate, dec_deallocate),
PROC(LAYOUTSTATS, enc_layoutstats, dec_layoutstats),
PROC(CLONE, enc_clone, dec_clone),
+ PROC(COPY, enc_copy, dec_copy),
#endif /* CONFIG_NFS_V4_2 */
};
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 9f80a086b..0b9e5cc9a 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -702,7 +702,7 @@ TRACE_EVENT(nfs_sillyrename_unlink,
),
TP_fast_assign(
- struct inode *dir = data->dir;
+ struct inode *dir = d_inode(data->dentry->d_parent);
size_t len = data->args.name.len;
__entry->dev = dir->i_sb->s_dev;
__entry->dir = NFS_FILEID(dir);
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1f6db4231..174dd4cf5 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -341,8 +341,10 @@ nfs_create_request(struct nfs_open_context *ctx, struct page *page,
* long write-back delay. This will be adjusted in
* update_nfs_request below if the region is not locked. */
req->wb_page = page;
- req->wb_index = page_file_index(page);
- get_page(page);
+ if (page) {
+ req->wb_index = page_file_index(page);
+ get_page(page);
+ }
req->wb_offset = offset;
req->wb_pgbase = offset;
req->wb_bytes = count;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 89a5ef4df..0fbe734cc 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -270,7 +270,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
};
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
- return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range);
+ return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range, 0);
}
static int
@@ -308,7 +308,7 @@ pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
spin_lock(&inode->i_lock);
pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
- pnfs_mark_matching_lsegs_invalid(lo, &head, &range);
+ pnfs_mark_matching_lsegs_invalid(lo, &head, &range, 0);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
@@ -361,8 +361,10 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
list_del_init(&lseg->pls_list);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
- if (list_empty(&lo->plh_segs))
+ if (list_empty(&lo->plh_segs)) {
+ set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
+ }
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
}
@@ -522,13 +524,35 @@ static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
return rv;
}
-/* Returns count of number of matching invalid lsegs remaining in list
- * after call.
+/*
+ * Compare 2 layout stateid sequence ids, to see which is newer,
+ * taking into account wraparound issues.
+ */
+static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
+{
+ return (s32)(s1 - s2) > 0;
+}
+
+/**
+ * pnfs_mark_matching_lsegs_invalid - tear down lsegs or mark them for later
+ * @lo: layout header containing the lsegs
+ * @tmp_list: list head where doomed lsegs should go
+ * @recall_range: optional recall range argument to match (may be NULL)
+ * @seq: only invalidate lsegs obtained prior to this sequence (may be 0)
+ *
+ * Walk the list of lsegs in the layout header, and tear down any that should
+ * be destroyed. If "recall_range" is specified then the segment must match
+ * that range. If "seq" is non-zero, then only match segments that were handed
+ * out at or before that sequence.
+ *
+ * Returns number of matching invalid lsegs remaining in list after scanning
+ * it and purging them.
*/
int
pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range)
+ const struct pnfs_layout_range *recall_range,
+ u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
@@ -540,10 +564,12 @@ pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (!recall_range ||
should_free_lseg(&lseg->pls_range, recall_range)) {
- dprintk("%s: freeing lseg %p iomode %d "
+ if (seq && pnfs_seqid_is_newer(lseg->pls_seq, seq))
+ continue;
+ dprintk("%s: freeing lseg %p iomode %d seq %u"
"offset %llu length %llu\n", __func__,
- lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
- lseg->pls_range.length);
+ lseg, lseg->pls_range.iomode, lseg->pls_seq,
+ lseg->pls_range.offset, lseg->pls_range.length);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
}
@@ -730,15 +756,6 @@ pnfs_destroy_all_layouts(struct nfs_client *clp)
pnfs_destroy_layouts_byclid(clp, false);
}
-/*
- * Compare 2 layout stateid sequence ids, to see which is newer,
- * taking into account wraparound issues.
- */
-static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
-{
- return (s32)(s1 - s2) > 0;
-}
-
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
@@ -781,50 +798,22 @@ pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
-int
-pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
- const struct pnfs_layout_range *range,
- struct nfs4_state *open_state)
-{
- int status = 0;
-
- dprintk("--> %s\n", __func__);
- spin_lock(&lo->plh_inode->i_lock);
- if (pnfs_layoutgets_blocked(lo)) {
- status = -EAGAIN;
- } else if (!nfs4_valid_open_stateid(open_state)) {
- status = -EBADF;
- } else if (list_empty(&lo->plh_segs) ||
- test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
- int seq;
-
- do {
- seq = read_seqbegin(&open_state->seqlock);
- nfs4_stateid_copy(dst, &open_state->stateid);
- } while (read_seqretry(&open_state->seqlock, seq));
- } else
- nfs4_stateid_copy(dst, &lo->plh_stateid);
- spin_unlock(&lo->plh_inode->i_lock);
- dprintk("<-- %s\n", __func__);
- return status;
-}
-
/*
-* Get layout from server.
-* for now, assume that whole file layouts are requested.
-* arg->offset: 0
-* arg->length: all ones
-*/
+ * Get layout from server.
+ * for now, assume that whole file layouts are requested.
+ * arg->offset: 0
+ * arg->length: all ones
+ */
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
struct nfs_open_context *ctx,
+ nfs4_stateid *stateid,
const struct pnfs_layout_range *range,
- gfp_t gfp_flags)
+ long *timeout, gfp_t gfp_flags)
{
struct inode *ino = lo->plh_inode;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs4_layoutget *lgp;
- struct pnfs_layout_segment *lseg;
loff_t i_size;
dprintk("--> %s\n", __func__);
@@ -834,40 +823,31 @@ send_layoutget(struct pnfs_layout_hdr *lo,
* store in lseg. If we race with a concurrent seqid morphing
* op, then re-send the LAYOUTGET.
*/
- do {
- lgp = kzalloc(sizeof(*lgp), gfp_flags);
- if (lgp == NULL)
- return NULL;
-
- i_size = i_size_read(ino);
-
- lgp->args.minlength = PAGE_SIZE;
- if (lgp->args.minlength > range->length)
- lgp->args.minlength = range->length;
- if (range->iomode == IOMODE_READ) {
- if (range->offset >= i_size)
- lgp->args.minlength = 0;
- else if (i_size - range->offset < lgp->args.minlength)
- lgp->args.minlength = i_size - range->offset;
- }
- lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
- pnfs_copy_range(&lgp->args.range, range);
- lgp->args.type = server->pnfs_curr_ld->id;
- lgp->args.inode = ino;
- lgp->args.ctx = get_nfs_open_context(ctx);
- lgp->gfp_flags = gfp_flags;
- lgp->cred = lo->plh_lc_cred;
-
- lseg = nfs4_proc_layoutget(lgp, gfp_flags);
- } while (lseg == ERR_PTR(-EAGAIN));
-
- if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg)))
- lseg = NULL;
- else
- pnfs_layout_clear_fail_bit(lo,
- pnfs_iomode_to_fail_bit(range->iomode));
+ lgp = kzalloc(sizeof(*lgp), gfp_flags);
+ if (lgp == NULL)
+ return ERR_PTR(-ENOMEM);
- return lseg;
+ i_size = i_size_read(ino);
+
+ lgp->args.minlength = PAGE_SIZE;
+ if (lgp->args.minlength > range->length)
+ lgp->args.minlength = range->length;
+ if (range->iomode == IOMODE_READ) {
+ if (range->offset >= i_size)
+ lgp->args.minlength = 0;
+ else if (i_size - range->offset < lgp->args.minlength)
+ lgp->args.minlength = i_size - range->offset;
+ }
+ lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
+ pnfs_copy_range(&lgp->args.range, range);
+ lgp->args.type = server->pnfs_curr_ld->id;
+ lgp->args.inode = ino;
+ lgp->args.ctx = get_nfs_open_context(ctx);
+ nfs4_stateid_copy(&lgp->args.stateid, stateid);
+ lgp->gfp_flags = gfp_flags;
+ lgp->cred = lo->plh_lc_cred;
+
+ return nfs4_proc_layoutget(lgp, timeout, gfp_flags);
}
static void pnfs_clear_layoutcommit(struct inode *inode,
@@ -899,6 +879,7 @@ pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
lo->plh_return_iomode = 0;
+ lo->plh_return_seq = 0;
pnfs_get_layout_hdr(lo);
clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
return true;
@@ -969,6 +950,7 @@ static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
bool send;
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
+ stateid.seqid = cpu_to_be32(lo->plh_return_seq);
iomode = lo->plh_return_iomode;
send = pnfs_prepare_layoutreturn(lo);
spin_unlock(&inode->i_lock);
@@ -1012,7 +994,7 @@ _pnfs_return_layout(struct inode *ino)
pnfs_get_layout_hdr(lo);
empty = list_empty(&lo->plh_segs);
pnfs_clear_layoutcommit(ino, &tmp_list);
- pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL, 0);
if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
struct pnfs_layout_range range = {
@@ -1310,6 +1292,7 @@ alloc_init_layout_hdr(struct inode *ino,
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
lo->plh_lc_cred = get_rpccred(ctx->cred);
+ lo->plh_flags |= 1 << NFS_LAYOUT_INVALID_STID;
return lo;
}
@@ -1317,6 +1300,8 @@ static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino,
struct nfs_open_context *ctx,
gfp_t gfp_flags)
+ __releases(&ino->i_lock)
+ __acquires(&ino->i_lock)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *new = NULL;
@@ -1341,23 +1326,28 @@ out_existing:
/*
* iomode matching rules:
- * iomode lseg match
- * ----- ----- -----
- * ANY READ true
- * ANY RW true
- * RW READ false
- * RW RW true
- * READ READ true
- * READ RW true
+ * iomode lseg strict match
+ * iomode
+ * ----- ----- ------ -----
+ * ANY READ N/A true
+ * ANY RW N/A true
+ * RW READ N/A false
+ * RW RW N/A true
+ * READ READ N/A true
+ * READ RW true false
+ * READ RW false true
*/
static bool
pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range,
- const struct pnfs_layout_range *range)
+ const struct pnfs_layout_range *range,
+ bool strict_iomode)
{
struct pnfs_layout_range range1;
if ((range->iomode == IOMODE_RW &&
ls_range->iomode != IOMODE_RW) ||
+ (range->iomode != ls_range->iomode &&
+ strict_iomode == true) ||
!pnfs_lseg_range_intersecting(ls_range, range))
return 0;
@@ -1372,7 +1362,8 @@ pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range,
*/
static struct pnfs_layout_segment *
pnfs_find_lseg(struct pnfs_layout_hdr *lo,
- struct pnfs_layout_range *range)
+ struct pnfs_layout_range *range,
+ bool strict_iomode)
{
struct pnfs_layout_segment *lseg, *ret = NULL;
@@ -1381,7 +1372,8 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
- pnfs_lseg_range_match(&lseg->pls_range, range)) {
+ pnfs_lseg_range_match(&lseg->pls_range, range,
+ strict_iomode)) {
ret = pnfs_get_lseg(lseg);
break;
}
@@ -1498,6 +1490,7 @@ pnfs_update_layout(struct inode *ino,
loff_t pos,
u64 count,
enum pnfs_iomode iomode,
+ bool strict_iomode,
gfp_t gfp_flags)
{
struct pnfs_layout_range arg = {
@@ -1505,27 +1498,30 @@ pnfs_update_layout(struct inode *ino,
.offset = pos,
.length = count,
};
- unsigned pg_offset;
+ unsigned pg_offset, seq;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs_client *clp = server->nfs_client;
- struct pnfs_layout_hdr *lo;
+ struct pnfs_layout_hdr *lo = NULL;
struct pnfs_layout_segment *lseg = NULL;
+ nfs4_stateid stateid;
+ long timeout = 0;
+ unsigned long giveup = jiffies + rpc_get_timeout(server->client);
bool first;
if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NO_PNFS);
goto out;
}
if (iomode == IOMODE_READ && i_size_read(ino) == 0) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
goto out;
}
if (pnfs_within_mdsthreshold(ctx, ino, iomode)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_MDSTHRESH);
goto out;
}
@@ -1536,14 +1532,14 @@ lookup_again:
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
spin_unlock(&ino->i_lock);
- trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_NOMEM);
goto out;
}
/* Do we even need to bother with this? */
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BULK_RECALL);
dprintk("%s matches recall, use MDS\n", __func__);
goto out_unlock;
@@ -1551,14 +1547,33 @@ lookup_again:
/* if LAYOUTGET already failed once we don't try again */
if (pnfs_layout_io_test_failed(lo, iomode)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
goto out_unlock;
}
- first = list_empty(&lo->plh_segs);
- if (first) {
- /* The first layoutget for the file. Need to serialize per
+ lseg = pnfs_find_lseg(lo, &arg, strict_iomode);
+ if (lseg) {
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_FOUND_CACHED);
+ goto out_unlock;
+ }
+
+ if (!nfs4_valid_open_stateid(ctx->state)) {
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
+ PNFS_UPDATE_LAYOUT_INVALID_OPEN);
+ goto out_unlock;
+ }
+
+ /*
+ * Choose a stateid for the LAYOUTGET. If we don't have a layout
+ * stateid, or it has been invalidated, then we must use the open
+ * stateid.
+ */
+ if (test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
+
+ /*
+ * The first layoutget for the file. Need to serialize per
* RFC 5661 Errata 3208.
*/
if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
@@ -1567,18 +1582,17 @@ lookup_again:
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
+ dprintk("%s retrying\n", __func__);
goto lookup_again;
}
+
+ first = true;
+ do {
+ seq = read_seqbegin(&ctx->state->seqlock);
+ nfs4_stateid_copy(&stateid, &ctx->state->stateid);
+ } while (read_seqretry(&ctx->state->seqlock, seq));
} else {
- /* Check to see if the layout for the given range
- * already exists
- */
- lseg = pnfs_find_lseg(lo, &arg);
- if (lseg) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
- PNFS_UPDATE_LAYOUT_FOUND_CACHED);
- goto out_unlock;
- }
+ nfs4_stateid_copy(&stateid, &lo->plh_stateid);
}
/*
@@ -1593,15 +1607,17 @@ lookup_again:
pnfs_clear_first_layoutget(lo);
pnfs_put_layout_hdr(lo);
dprintk("%s retrying\n", __func__);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg, PNFS_UPDATE_LAYOUT_RETRY);
goto lookup_again;
}
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_RETURN);
goto out_put_layout_hdr;
}
if (pnfs_layoutgets_blocked(lo)) {
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_BLOCKED);
goto out_unlock;
}
@@ -1626,10 +1642,36 @@ lookup_again:
if (arg.length != NFS4_MAX_UINT64)
arg.length = PAGE_ALIGN(arg.length);
- lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
- atomic_dec(&lo->plh_outstanding);
- trace_pnfs_update_layout(ino, pos, count, iomode, lo,
+ lseg = send_layoutget(lo, ctx, &stateid, &arg, &timeout, gfp_flags);
+ trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg,
PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
+ if (IS_ERR(lseg)) {
+ switch(PTR_ERR(lseg)) {
+ case -ERECALLCONFLICT:
+ if (time_after(jiffies, giveup))
+ lseg = NULL;
+ /* Fallthrough */
+ case -EAGAIN:
+ pnfs_put_layout_hdr(lo);
+ if (first)
+ pnfs_clear_first_layoutget(lo);
+ if (lseg) {
+ trace_pnfs_update_layout(ino, pos, count,
+ iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY);
+ goto lookup_again;
+ }
+ /* Fallthrough */
+ default:
+ if (!nfs_error_is_fatal(PTR_ERR(lseg))) {
+ pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+ lseg = NULL;
+ }
+ }
+ } else {
+ pnfs_layout_clear_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
+ }
+
+ atomic_dec(&lo->plh_outstanding);
out_put_layout_hdr:
if (first)
pnfs_clear_first_layoutget(lo);
@@ -1678,38 +1720,36 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
struct pnfs_layout_segment *lseg;
struct inode *ino = lo->plh_inode;
LIST_HEAD(free_me);
- int status = -EINVAL;
if (!pnfs_sanity_check_layout_range(&res->range))
- goto out;
+ return ERR_PTR(-EINVAL);
/* Inject layout blob into I/O device driver */
lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags);
- if (!lseg || IS_ERR(lseg)) {
+ if (IS_ERR_OR_NULL(lseg)) {
if (!lseg)
- status = -ENOMEM;
- else
- status = PTR_ERR(lseg);
- dprintk("%s: Could not allocate layout: error %d\n",
- __func__, status);
- goto out;
+ lseg = ERR_PTR(-ENOMEM);
+
+ dprintk("%s: Could not allocate layout: error %ld\n",
+ __func__, PTR_ERR(lseg));
+ return lseg;
}
init_lseg(lo, lseg);
lseg->pls_range = res->range;
+ lseg->pls_seq = be32_to_cpu(res->stateid.seqid);
spin_lock(&ino->i_lock);
if (pnfs_layoutgets_blocked(lo)) {
dprintk("%s forget reply due to state\n", __func__);
- goto out_forget_reply;
+ goto out_forget;
}
if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
dprintk("%s forget reply due to sequence\n", __func__);
- status = -EAGAIN;
- goto out_forget_reply;
+ goto out_forget;
}
pnfs_set_layout_stateid(lo, &res->stateid, false);
} else {
@@ -1718,7 +1758,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
* inode invalid, and don't bother validating the stateid
* sequence number.
*/
- pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL);
+ pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL, 0);
nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
@@ -1735,18 +1775,17 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&free_me);
return lseg;
-out:
- return ERR_PTR(status);
-out_forget_reply:
+out_forget:
spin_unlock(&ino->i_lock);
lseg->pls_layout = lo;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
- goto out;
+ return ERR_PTR(-EAGAIN);
}
static void
-pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
+pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
+ u32 seq)
{
if (lo->plh_return_iomode == iomode)
return;
@@ -1754,6 +1793,8 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
iomode = IOMODE_ANY;
lo->plh_return_iomode = iomode;
set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+ if (!lo->plh_return_seq || pnfs_seqid_is_newer(seq, lo->plh_return_seq))
+ lo->plh_return_seq = seq;
}
/**
@@ -1769,7 +1810,8 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
int
pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *return_range)
+ const struct pnfs_layout_range *return_range,
+ u32 seq)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
@@ -1792,8 +1834,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
continue;
remaining++;
set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
- pnfs_set_plh_return_iomode(lo, return_range->iomode);
}
+
+ if (remaining)
+ pnfs_set_plh_return_info(lo, return_range->iomode, seq);
+
return remaining;
}
@@ -1810,13 +1855,14 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
bool return_now = false;
spin_lock(&inode->i_lock);
- pnfs_set_plh_return_iomode(lo, range.iomode);
+ pnfs_set_plh_return_info(lo, range.iomode, lseg->pls_seq);
/*
* mark all matching lsegs so that we are sure to have no live
* segments at hand when sending layoutreturn. See pnfs_put_lseg()
* for how it works.
*/
- if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) {
+ if (!pnfs_mark_matching_lsegs_return(lo, &free_me,
+ &range, lseg->pls_seq)) {
nfs4_stateid stateid;
enum pnfs_iomode iomode = lo->plh_return_iomode;
@@ -1849,6 +1895,7 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
req_offset(req),
rd_size,
IOMODE_READ,
+ false,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -1873,6 +1920,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
req_offset(req),
wb_size,
IOMODE_RW,
+ false,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
@@ -2143,12 +2191,15 @@ pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
}
/* Resend all requests through pnfs. */
-int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
{
struct nfs_pageio_descriptor pgio;
- nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops);
- return nfs_pageio_resend(&pgio, hdr);
+ if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+ nfs_pageio_init_read(&pgio, hdr->inode, false,
+ hdr->completion_ops);
+ hdr->task.tk_status = nfs_pageio_resend(&pgio, hdr);
+ }
}
EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs);
@@ -2158,12 +2209,11 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
- int err = 0;
trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
if (trypnfs == PNFS_TRY_AGAIN)
- err = pnfs_read_resend_pnfs(hdr);
- if (trypnfs == PNFS_NOT_ATTEMPTED || err)
+ pnfs_read_resend_pnfs(hdr);
+ if (trypnfs == PNFS_NOT_ATTEMPTED || hdr->task.tk_status)
pnfs_read_through_mds(desc, hdr);
}
@@ -2405,7 +2455,7 @@ pnfs_report_layoutstat(struct inode *inode, gfp_t gfp_flags)
spin_lock(&inode->i_lock);
if (!NFS_I(inode)->layout) {
spin_unlock(&inode->i_lock);
- goto out;
+ goto out_clear_layoutstats;
}
hdr = NFS_I(inode)->layout;
pnfs_get_layout_hdr(hdr);
@@ -2434,6 +2484,7 @@ out_free:
kfree(data);
out_put:
pnfs_put_layout_hdr(hdr);
+out_clear_layoutstats:
smp_mb__before_atomic();
clear_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags);
smp_mb__after_atomic();
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 1ac1db5f6..b21bd0bee 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -64,6 +64,7 @@ struct pnfs_layout_segment {
struct list_head pls_lc_list;
struct pnfs_layout_range pls_range;
atomic_t pls_refcount;
+ u32 pls_seq;
unsigned long pls_flags;
struct pnfs_layout_hdr *pls_layout;
struct work_struct pls_work;
@@ -194,6 +195,7 @@ struct pnfs_layout_hdr {
unsigned long plh_flags;
nfs4_stateid plh_stateid;
u32 plh_barrier; /* ignore lower seqids */
+ u32 plh_return_seq;
enum pnfs_iomode plh_return_iomode;
loff_t plh_lwb; /* last write byte for layoutcommit */
struct rpc_cred *plh_lc_cred; /* layoutcommit cred */
@@ -226,7 +228,7 @@ extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
extern int nfs4_proc_getdeviceinfo(struct nfs_server *server,
struct pnfs_device *dev,
struct rpc_cred *cred);
-extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags);
+extern struct pnfs_layout_segment* nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags);
extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp, bool sync);
/* pnfs.c */
@@ -258,16 +260,14 @@ void pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo);
void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
const nfs4_stateid *new,
bool update_barrier);
-int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
- struct pnfs_layout_hdr *lo,
- const struct pnfs_layout_range *range,
- struct nfs4_state *open_state);
int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range);
+ const struct pnfs_layout_range *recall_range,
+ u32 seq);
int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
- const struct pnfs_layout_range *recall_range);
+ const struct pnfs_layout_range *recall_range,
+ u32 seq);
bool pnfs_roc(struct inode *ino);
void pnfs_roc_release(struct inode *ino);
void pnfs_roc_set_barrier(struct inode *ino, u32 barrier);
@@ -282,12 +282,13 @@ int _pnfs_return_layout(struct inode *);
int pnfs_commit_and_return_layout(struct inode *);
void pnfs_ld_write_done(struct nfs_pgio_header *);
void pnfs_ld_read_done(struct nfs_pgio_header *);
-int pnfs_read_resend_pnfs(struct nfs_pgio_header *);
+void pnfs_read_resend_pnfs(struct nfs_pgio_header *);
struct pnfs_layout_segment *pnfs_update_layout(struct inode *ino,
struct nfs_open_context *ctx,
loff_t pos,
u64 count,
enum pnfs_iomode iomode,
+ bool strict_iomode,
gfp_t gfp_flags);
void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo);
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index dcb70001a..b38e3c0dc 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -61,7 +61,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);
/* The generic layer is about to remove the req from the commit list.
* If this will make the bucket empty, it will need to put the lseg reference.
- * Note this must be called holding the inode (/cinfo) lock
+ * Note this must be called holding i_lock
*/
void
pnfs_generic_clear_request_commit(struct nfs_page *req,
@@ -98,7 +98,7 @@ pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
if (!nfs_lock_request(req))
continue;
kref_get(&req->wb_kref);
- if (cond_resched_lock(cinfo->lock))
+ if (cond_resched_lock(&cinfo->inode->i_lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
@@ -119,7 +119,7 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
struct list_head *dst = &bucket->committing;
int ret;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
if (ret) {
cinfo->ds->nwritten -= ret;
@@ -142,7 +142,7 @@ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
{
int i, rv = 0, cnt;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
cinfo, max);
@@ -161,16 +161,16 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst,
struct pnfs_layout_segment *freeme;
int i;
- lockdep_assert_held(cinfo->lock);
+ lockdep_assert_held(&cinfo->inode->i_lock);
restart:
for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
if (pnfs_generic_transfer_commit_list(&b->written, dst,
cinfo, 0)) {
freeme = b->wlseg;
b->wlseg = NULL;
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
pnfs_put_lseg(freeme);
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
goto restart;
}
}
@@ -186,7 +186,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
LIST_HEAD(pages);
int i;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
for (i = idx; i < fl_cinfo->nbuckets; i++) {
bucket = &fl_cinfo->buckets[i];
if (list_empty(&bucket->committing))
@@ -194,12 +194,12 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
freeme = bucket->clseg;
bucket->clseg = NULL;
list_splice_init(&bucket->committing, &pages);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
nfs_retry_commit(&pages, freeme, cinfo, i);
pnfs_put_lseg(freeme);
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
static unsigned int
@@ -238,11 +238,11 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
struct pnfs_commit_bucket *bucket;
bucket = &cinfo->ds->buckets[data->ds_commit_index];
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
list_splice_init(&bucket->committing, pages);
data->lseg = bucket->clseg;
bucket->clseg = NULL;
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
}
@@ -910,12 +910,12 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
struct list_head *list;
struct pnfs_commit_bucket *buckets;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
buckets = cinfo->ds->buckets;
list = &buckets[ds_commit_idx].written;
if (list_empty(list)) {
if (!pnfs_is_valid_lseg(lseg)) {
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
cinfo->completion_ops->resched_write(cinfo, req);
return;
}
@@ -932,7 +932,7 @@ pnfs_layout_mark_request_commit(struct nfs_page *req,
cinfo->ds->nwritten++;
nfs_request_add_commit_list_locked(req, list, cinfo);
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
nfs_mark_page_unstable(req->wb_page, cinfo);
}
EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f12682802..2137e0202 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -191,6 +191,7 @@ static const match_table_t nfs_mount_option_tokens = {
enum {
Opt_xprt_udp, Opt_xprt_udp6, Opt_xprt_tcp, Opt_xprt_tcp6, Opt_xprt_rdma,
+ Opt_xprt_rdma6,
Opt_xprt_err
};
@@ -201,6 +202,7 @@ static const match_table_t nfs_xprt_protocol_tokens = {
{ Opt_xprt_tcp, "tcp" },
{ Opt_xprt_tcp6, "tcp6" },
{ Opt_xprt_rdma, "rdma" },
+ { Opt_xprt_rdma6, "rdma6" },
{ Opt_xprt_err, NULL }
};
@@ -1456,6 +1458,8 @@ static int nfs_parse_mount_options(char *raw,
mnt->flags |= NFS_MOUNT_TCP;
mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
break;
+ case Opt_xprt_rdma6:
+ protofamily = AF_INET6;
case Opt_xprt_rdma:
/* vector side protocols to TCP */
mnt->flags |= NFS_MOUNT_TCP;
@@ -2408,6 +2412,11 @@ static int nfs_compare_super_address(struct nfs_server *server1,
struct nfs_server *server2)
{
struct sockaddr *sap1, *sap2;
+ struct rpc_xprt *xprt1 = server1->client->cl_xprt;
+ struct rpc_xprt *xprt2 = server2->client->cl_xprt;
+
+ if (!net_eq(xprt1->xprt_net, xprt2->xprt_net))
+ return 0;
sap1 = (struct sockaddr *)&server1->nfs_client->cl_addr;
sap2 = (struct sockaddr *)&server2->nfs_client->cl_addr;
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index fa538b2ba..1868246f5 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -30,45 +30,11 @@
static void
nfs_free_unlinkdata(struct nfs_unlinkdata *data)
{
- iput(data->dir);
put_rpccred(data->cred);
kfree(data->args.name.name);
kfree(data);
}
-#define NAME_ALLOC_LEN(len) ((len+16) & ~15)
-/**
- * nfs_copy_dname - copy dentry name to data structure
- * @dentry: pointer to dentry
- * @data: nfs_unlinkdata
- */
-static int nfs_copy_dname(struct dentry *dentry, struct nfs_unlinkdata *data)
-{
- char *str;
- int len = dentry->d_name.len;
-
- str = kmemdup(dentry->d_name.name, NAME_ALLOC_LEN(len), GFP_KERNEL);
- if (!str)
- return -ENOMEM;
- data->args.name.len = len;
- data->args.name.name = str;
- return 0;
-}
-
-static void nfs_free_dname(struct nfs_unlinkdata *data)
-{
- kfree(data->args.name.name);
- data->args.name.name = NULL;
- data->args.name.len = 0;
-}
-
-static void nfs_dec_sillycount(struct inode *dir)
-{
- struct nfs_inode *nfsi = NFS_I(dir);
- if (atomic_dec_return(&nfsi->silly_count) == 1)
- wake_up(&nfsi->waitqueue);
-}
-
/**
* nfs_async_unlink_done - Sillydelete post-processing
* @task: rpc_task of the sillydelete
@@ -78,7 +44,7 @@ static void nfs_dec_sillycount(struct inode *dir)
static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- struct inode *dir = data->dir;
+ struct inode *dir = d_inode(data->dentry->d_parent);
trace_nfs_sillyrename_unlink(data, task->tk_status);
if (!NFS_PROTO(dir)->unlink_done(task, dir))
@@ -95,17 +61,21 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
static void nfs_async_unlink_release(void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- struct super_block *sb = data->dir->i_sb;
+ struct dentry *dentry = data->dentry;
+ struct super_block *sb = dentry->d_sb;
- nfs_dec_sillycount(data->dir);
+ up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
+ d_lookup_done(dentry);
nfs_free_unlinkdata(data);
+ dput(dentry);
nfs_sb_deactive(sb);
}
static void nfs_unlink_prepare(struct rpc_task *task, void *calldata)
{
struct nfs_unlinkdata *data = calldata;
- NFS_PROTO(data->dir)->unlink_rpc_prepare(task, data);
+ struct inode *dir = d_inode(data->dentry->d_parent);
+ NFS_PROTO(dir)->unlink_rpc_prepare(task, data);
}
static const struct rpc_call_ops nfs_unlink_ops = {
@@ -114,7 +84,7 @@ static const struct rpc_call_ops nfs_unlink_ops = {
.rpc_call_prepare = nfs_unlink_prepare,
};
-static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct nfs_unlinkdata *data)
+static void nfs_do_call_unlink(struct nfs_unlinkdata *data)
{
struct rpc_message msg = {
.rpc_argp = &data->args,
@@ -129,10 +99,31 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
.flags = RPC_TASK_ASYNC,
};
struct rpc_task *task;
+ struct inode *dir = d_inode(data->dentry->d_parent);
+ nfs_sb_active(dir->i_sb);
+ data->args.fh = NFS_FH(dir);
+ nfs_fattr_init(data->res.dir_attr);
+
+ NFS_PROTO(dir)->unlink_setup(&msg, dir);
+
+ task_setup_data.rpc_client = NFS_CLIENT(dir);
+ task = rpc_run_task(&task_setup_data);
+ if (!IS_ERR(task))
+ rpc_put_task_async(task);
+}
+
+static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
+{
+ struct inode *dir = d_inode(dentry->d_parent);
struct dentry *alias;
- alias = d_lookup(parent, &data->args.name);
- if (alias != NULL) {
+ down_read_non_owner(&NFS_I(dir)->rmdir_sem);
+ alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq);
+ if (IS_ERR(alias)) {
+ up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+ return 0;
+ }
+ if (!d_in_lookup(alias)) {
int ret;
void *devname_garbage = NULL;
@@ -140,10 +131,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
* Hey, we raced with lookup... See if we need to transfer
* the sillyrename information to the aliased dentry.
*/
- nfs_free_dname(data);
- ret = nfs_copy_dname(alias, data);
spin_lock(&alias->d_lock);
- if (ret == 0 && d_really_is_positive(alias) &&
+ if (d_really_is_positive(alias) &&
!(alias->d_flags & DCACHE_NFSFS_RENAMED)) {
devname_garbage = alias->d_fsdata;
alias->d_fsdata = data;
@@ -152,8 +141,8 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
} else
ret = 0;
spin_unlock(&alias->d_lock);
- nfs_dec_sillycount(dir);
dput(alias);
+ up_read_non_owner(&NFS_I(dir)->rmdir_sem);
/*
* If we'd displaced old cached devname, free it. At that
* point dentry is definitely not a root, so we won't need
@@ -162,94 +151,18 @@ static int nfs_do_call_unlink(struct dentry *parent, struct inode *dir, struct n
kfree(devname_garbage);
return ret;
}
- data->dir = igrab(dir);
- if (!data->dir) {
- nfs_dec_sillycount(dir);
- return 0;
- }
- nfs_sb_active(dir->i_sb);
- data->args.fh = NFS_FH(dir);
- nfs_fattr_init(data->res.dir_attr);
-
- NFS_PROTO(dir)->unlink_setup(&msg, dir);
-
- task_setup_data.rpc_client = NFS_CLIENT(dir);
- task = rpc_run_task(&task_setup_data);
- if (!IS_ERR(task))
- rpc_put_task_async(task);
+ data->dentry = alias;
+ nfs_do_call_unlink(data);
return 1;
}
-static int nfs_call_unlink(struct dentry *dentry, struct nfs_unlinkdata *data)
-{
- struct dentry *parent;
- struct inode *dir;
- int ret = 0;
-
-
- parent = dget_parent(dentry);
- if (parent == NULL)
- goto out_free;
- dir = d_inode(parent);
- /* Non-exclusive lock protects against concurrent lookup() calls */
- spin_lock(&dir->i_lock);
- if (atomic_inc_not_zero(&NFS_I(dir)->silly_count) == 0) {
- /* Deferred delete */
- hlist_add_head(&data->list, &NFS_I(dir)->silly_list);
- spin_unlock(&dir->i_lock);
- ret = 1;
- goto out_dput;
- }
- spin_unlock(&dir->i_lock);
- ret = nfs_do_call_unlink(parent, dir, data);
-out_dput:
- dput(parent);
-out_free:
- return ret;
-}
-
-void nfs_wait_on_sillyrename(struct dentry *dentry)
-{
- struct nfs_inode *nfsi = NFS_I(d_inode(dentry));
-
- wait_event(nfsi->waitqueue, atomic_read(&nfsi->silly_count) <= 1);
-}
-
-void nfs_block_sillyrename(struct dentry *dentry)
-{
- struct nfs_inode *nfsi = NFS_I(d_inode(dentry));
-
- wait_event(nfsi->waitqueue, atomic_cmpxchg(&nfsi->silly_count, 1, 0) == 1);
-}
-
-void nfs_unblock_sillyrename(struct dentry *dentry)
-{
- struct inode *dir = d_inode(dentry);
- struct nfs_inode *nfsi = NFS_I(dir);
- struct nfs_unlinkdata *data;
-
- atomic_inc(&nfsi->silly_count);
- spin_lock(&dir->i_lock);
- while (!hlist_empty(&nfsi->silly_list)) {
- if (!atomic_inc_not_zero(&nfsi->silly_count))
- break;
- data = hlist_entry(nfsi->silly_list.first, struct nfs_unlinkdata, list);
- hlist_del(&data->list);
- spin_unlock(&dir->i_lock);
- if (nfs_do_call_unlink(dentry, dir, data) == 0)
- nfs_free_unlinkdata(data);
- spin_lock(&dir->i_lock);
- }
- spin_unlock(&dir->i_lock);
-}
-
/**
* nfs_async_unlink - asynchronous unlinking of a file
* @dir: parent directory of dentry
* @dentry: dentry to unlink
*/
static int
-nfs_async_unlink(struct inode *dir, struct dentry *dentry)
+nfs_async_unlink(struct dentry *dentry, struct qstr *name)
{
struct nfs_unlinkdata *data;
int status = -ENOMEM;
@@ -258,13 +171,18 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
data = kzalloc(sizeof(*data), GFP_KERNEL);
if (data == NULL)
goto out;
+ data->args.name.name = kstrdup(name->name, GFP_KERNEL);
+ if (!data->args.name.name)
+ goto out_free;
+ data->args.name.len = name->len;
data->cred = rpc_lookup_cred();
if (IS_ERR(data->cred)) {
status = PTR_ERR(data->cred);
- goto out_free;
+ goto out_free_name;
}
data->res.dir_attr = &data->dir_attr;
+ init_waitqueue_head(&data->wq);
status = -EBUSY;
spin_lock(&dentry->d_lock);
@@ -284,6 +202,8 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry)
out_unlock:
spin_unlock(&dentry->d_lock);
put_rpccred(data->cred);
+out_free_name:
+ kfree(data->args.name.name);
out_free:
kfree(data);
out:
@@ -302,17 +222,15 @@ out:
void
nfs_complete_unlink(struct dentry *dentry, struct inode *inode)
{
- struct nfs_unlinkdata *data = NULL;
+ struct nfs_unlinkdata *data;
spin_lock(&dentry->d_lock);
- if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
- dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
- data = dentry->d_fsdata;
- dentry->d_fsdata = NULL;
- }
+ dentry->d_flags &= ~DCACHE_NFSFS_RENAMED;
+ data = dentry->d_fsdata;
+ dentry->d_fsdata = NULL;
spin_unlock(&dentry->d_lock);
- if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data)))
+ if (NFS_STALE(inode) || !nfs_call_unlink(dentry, data))
nfs_free_unlinkdata(data);
}
@@ -559,18 +477,10 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry)
/* queue unlink first. Can't do this from rpc_release as it
* has to allocate memory
*/
- error = nfs_async_unlink(dir, dentry);
+ error = nfs_async_unlink(dentry, &sdentry->d_name);
if (error)
goto out_dput;
- /* populate unlinkdata with the right dname */
- error = nfs_copy_dname(sdentry,
- (struct nfs_unlinkdata *)dentry->d_fsdata);
- if (error) {
- nfs_cancel_async_unlink(dentry);
- goto out_dput;
- }
-
/* run the rename task, undo unlink if it fails */
task = nfs_async_rename(dir, dir, dentry, sdentry,
nfs_complete_sillyrename);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index f5e613395..e1c74d3db 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -245,8 +245,7 @@ static void nfs_mark_uptodate(struct nfs_page *req)
static int wb_priority(struct writeback_control *wbc)
{
int ret = 0;
- if (wbc->for_reclaim)
- return FLUSH_HIGHPRI | FLUSH_COND_STABLE;
+
if (wbc->sync_mode == WB_SYNC_ALL)
ret = FLUSH_COND_STABLE;
return ret;
@@ -737,7 +736,7 @@ static void nfs_inode_remove_request(struct nfs_page *req)
head = req->wb_head;
spin_lock(&inode->i_lock);
- if (likely(!PageSwapCache(head->wb_page))) {
+ if (likely(head->wb_page && !PageSwapCache(head->wb_page))) {
set_page_private(head->wb_page, 0);
ClearPagePrivate(head->wb_page);
smp_mb__after_atomic();
@@ -759,7 +758,8 @@ static void nfs_inode_remove_request(struct nfs_page *req)
static void
nfs_mark_request_dirty(struct nfs_page *req)
{
- __set_page_dirty_nobuffers(req->wb_page);
+ if (req->wb_page)
+ __set_page_dirty_nobuffers(req->wb_page);
}
/*
@@ -804,7 +804,7 @@ nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
* number of outstanding requests requiring a commit as well as
* the MM page stats.
*
- * The caller must hold the cinfo->lock, and the nfs_page lock.
+ * The caller must hold cinfo->inode->i_lock, and the nfs_page lock.
*/
void
nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst,
@@ -832,10 +832,11 @@ EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked);
void
nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo);
- spin_unlock(cinfo->lock);
- nfs_mark_page_unstable(req->wb_page, cinfo);
+ spin_unlock(&cinfo->inode->i_lock);
+ if (req->wb_page)
+ nfs_mark_page_unstable(req->wb_page, cinfo);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);
@@ -864,7 +865,7 @@ EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
struct inode *inode)
{
- cinfo->lock = &inode->i_lock;
+ cinfo->inode = inode;
cinfo->mds = &NFS_I(inode)->commit_info;
cinfo->ds = pnfs_get_ds_info(inode);
cinfo->dreq = NULL;
@@ -967,7 +968,7 @@ nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
return cinfo->mds->ncommit;
}
-/* cinfo->lock held by caller */
+/* cinfo->inode->i_lock held by caller */
int
nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
struct nfs_commit_info *cinfo, int max)
@@ -979,7 +980,7 @@ nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
if (!nfs_lock_request(req))
continue;
kref_get(&req->wb_kref);
- if (cond_resched_lock(cinfo->lock))
+ if (cond_resched_lock(&cinfo->inode->i_lock))
list_safe_reset_next(req, tmp, wb_list);
nfs_request_remove_commit_list(req, cinfo);
nfs_list_add_request(req, dst);
@@ -1005,7 +1006,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
{
int ret = 0;
- spin_lock(cinfo->lock);
+ spin_lock(&cinfo->inode->i_lock);
if (cinfo->mds->ncommit > 0) {
const int max = INT_MAX;
@@ -1013,7 +1014,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst,
cinfo, max);
ret += pnfs_scan_commit_lists(inode, cinfo, max - ret);
}
- spin_unlock(cinfo->lock);
+ spin_unlock(&cinfo->inode->i_lock);
return ret;
}
@@ -1728,6 +1729,36 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
return -ENOMEM;
}
+int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf)
+{
+ struct inode *inode = file_inode(file);
+ struct nfs_open_context *open;
+ struct nfs_commit_info cinfo;
+ struct nfs_page *req;
+ int ret;
+
+ open = get_nfs_open_context(nfs_file_open_context(file));
+ req = nfs_create_request(open, NULL, NULL, 0, i_size_read(inode));
+ if (IS_ERR(req)) {
+ ret = PTR_ERR(req);
+ goto out_put;
+ }
+
+ nfs_init_cinfo_from_inode(&cinfo, inode);
+
+ memcpy(&req->wb_verf, verf, sizeof(struct nfs_write_verifier));
+ nfs_request_add_commit_list(req, &cinfo);
+ ret = nfs_commit_inode(inode, FLUSH_SYNC);
+ if (ret > 0)
+ ret = 0;
+
+ nfs_free_request(req);
+out_put:
+ put_nfs_open_context(open);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_commit_file);
+
/*
* COMMIT call returned
*/
@@ -1752,7 +1783,8 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
while (!list_empty(&data->pages)) {
req = nfs_list_entry(data->pages.next);
nfs_list_remove_request(req);
- nfs_clear_page_commit(req->wb_page);
+ if (req->wb_page)
+ nfs_clear_page_commit(req->wb_page);
dprintk("NFS: commit (%s/%llu %d@%lld)",
req->wb_context->dentry->d_sb->s_id,